Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3460
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures in programming and functional programming, particularly in Haskell

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Démographie
    -0.43
    URLException
    -0.41
     مشين
    -0.40
    InjectAttribute
    -0.39
     pieles
    -0.38
    CrossRef
    -0.38
    ➋
    -0.38
    PathVariable
    -0.37
    bootstrapcdn
    -0.36
    脚注の使い方
    -0.36
    POSITIVE LOGITS
    Билгалдахарш
    0.65
    cljs
    0.56
     immutable
    0.53
    Composable
    0.51
    __((
    0.50
    immutable
    0.48
     immu
    0.47
     nakalista
    0.46
    elemField
    0.44
    XtraReports
    0.43
    Activations Density 0.556%

    No Known Activations