© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 107750
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and function definitions related to creating and manipulating objects or classes

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

    code related to functions and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.53
    /*
    -0.47
     թվական
    -0.40
    devamını
    -0.38
    ----+
    -0.37
     utafitiHapana
    -0.37
    rzez
    -0.37
    ộn
    -0.37
     AssemblyCulture
    -0.36
     Szcz
    -0.36
    POSITIVE LOGITS
    setAttribute
    1.07
    addAttribute
    0.81
    flashdata
    0.65
     astore
    0.63
    Geplaatst
    0.58
    hashtags
    0.53
    putExtra
    0.53
    HtmlAttribute
    0.51
     ModelExpression
    0.50
     Serbie
    0.50
    Activations Density 0.002%

    No Known Activations