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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8820
    Prev
    Next
    INDEX
    Explanations

    elements related to web page navigation and file management structures in code

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

    HTML and code markup tags and class/attribute names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     الحره
    -0.87
     يتيمه
    -0.85
    rungsseite
    -0.81
     nahilalakip
    -0.75
     otomatig
    -0.73
     ivelany
    -0.73
     beginnetje
    -0.72
    \{\\
    -0.71
     disambiguazione
    -0.71
    awtextra
    -0.70
    POSITIVE LOGITS
    Po
    0.48
    toBe
    0.48
    Man
    0.47
    Vi
    0.46
    Le
    0.44
    Pra
    0.43
    Mac
    0.42
    Pro
    0.42
    Or
    0.42
    Hi
    0.41
    Activations Density 0.883%

    No Known Activations