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

    Neuronpedia

    APICircuit 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 40746
    Prev
    Next
    INDEX
    Explanations

    colons and their variations in numerical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     jspb
    -0.54
     makeStyles
    -0.46
     initComponents
    -0.45
    ScopeManager
    -0.43
     AssemblyTitle
    -0.43
     Réponses
    -0.42
     Walkover
    -0.42
    DIPSETTING
    -0.40
    TypedDataSet
    -0.38
     kaarangay
    -0.38
    POSITIVE LOGITS
    
    0.52
    thenReturn
    0.48
    Билгалдахарш
    0.45
    İstinadlar
    0.44
    consulté
    0.43
    +#+
    0.42
    entur
    0.42
     bä
    0.41
    Filter
    0.41
     drunk
    0.41
    Activations Density 0.000%

    No Known Activations