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. 12200
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to components and structures in technical or scientific contexts

    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
     resourceCulture
    -0.42
    DataPropertyName
    -0.41
    Géographie
    -0.38
     Semiconductor
    -0.38
    举
    -0.36
    entierung
    -0.36
    preuve
    -0.35
    EDOM
    -0.35
     seeded
    -0.34
    避け
    -0.34
    POSITIVE LOGITS
     HttpNotFound
    0.63
    المناصب
    0.58
     ModelExpression
    0.58
     صوتيه
    0.53
    ंदीखरीदारी
    0.53
    pushFollow
    0.52
     tartalomajánló
    0.50
    évaluateur
    0.49
     <>",
    0.46
    optionalTypeArgs
    0.46
    Activations Density 1.387%

    No Known Activations