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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 3408
    Prev
    Next
    INDEX
    Explanations

    instances of personal and familial identification or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.84
     Савезне
    -0.76
    :✨
    -0.74
    лтамалар
    -0.71
     Numerade
    -0.71
     Италијани
    -0.69
     Wikimedijinoj
    -0.69
     autorytatywna
    -0.67
    Autoritní
    -0.67
    ंदीखरीदारी
    -0.63
    POSITIVE LOGITS
     NUKAT
    0.34
    AnchorTagHelper
    0.33
    EndContext
    0.32
    (!__
    0.32
    ButterKnife
    0.30
    formik
    0.29
    WriteBarrier
    0.29
    WithIdentifier
    0.29
    ArgsConstructor
    0.29
    IsMutable
    0.28
    Activations Density 20.794%

    No Known Activations