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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12207
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and family relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.57
    Parcelize
    -0.45
     bio
    -0.43
    setVerticalGroup
    -0.42
     analyses
    -0.42
     autorytatywna
    -0.40
    以前
    -0.40
    MENAFN
    -0.39
     toch
    -0.39
    ならず
    -0.39
    POSITIVE LOGITS
     estekak
    0.59
     виправивши
    0.53
    horabuena
    0.52
     Савезне
    0.48
    rąg
    0.44
     ویکی‌پدیای
    0.43
     hâte
    0.42
     ModelExpression
    0.41
     ſta
    0.41
    Referències
    0.41
    Activations Density 0.122%

    No Known Activations