© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 601
    Prev
    Next
    INDEX
    Explanations

    UI elements and their associated identifiers in a programming context, particularly related to visibility and management of components

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

    camelCase identifiers and property names in code.

    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
     kasarigan
    -0.92
    IntoConstraints
    -0.76
    تقاوى
    -0.73
    ſicht
    -0.73
     resourceCulture
    -0.73
     Italijanski
    -0.71
     Chwiliwch
    -0.71
     iprot
    -0.70
    +#+#
    -0.69
    InitVars
    -0.68
    POSITIVE LOGITS
     value
    0.41
    value
    0.37
     thingy
    0.35
     만들
    0.35
    effetto
    0.33
     holder
    0.33
     будто
    0.33
     Gebir
    0.33
     notation
    0.32
     Prüfung
    0.32
    Activations Density 0.679%

    No Known Activations