© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3933
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript structures related to navigation bars and collapsible elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML and code markup structures with nested elements and attributes.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    HTML/JavaScript code related to collapsible UI elements like accordions, navbars, and panels.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to collapsible UI components and their controls in code or markup (e.g., accordion/collapse panels, navbars, expand/collapse actions).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.43
    NOPQRST
    -0.42
     tama
    -0.40
     Tama
    -0.38
    cipais
    -0.38
    Ӕ
    -0.38
    ContentAlignment
    -0.38
    ⓧ
    -0.37
    almaz
    -0.37
    qrstuvwxyz
    -0.36
    POSITIVE LOGITS
     collapse
    1.13
     expanded
    1.10
     expansion
    1.10
    collapse
    1.10
     collapsed
    1.09
     expand
    1.07
     Collapse
    1.05
    Collapse
    1.02
     collapsible
    1.02
     Expansion
    1.00
    Activations Density 0.320%

    No Known Activations