© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15546
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and concepts, especially related to prime factors and divisors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    sizeCache
    -0.61
    genodigd
    -0.59
    nvarchar
    -0.54
    Бахар
    -0.53
    ſcher
    -0.53
    لينكات
    -0.53
     enfans
    -0.53
    IntoConstraints
    -0.51
     dieſen
    -0.49
    IsMutable
    -0.49
    POSITIVE LOGITS
     Regardless
    0.36
    AndEndTag
    0.35
    Regardless
    0.35
    Demikian
    0.35
     regardless
    0.34
     cho
    0.33
    tonode
    0.32
     Live
    0.32
     ente
    0.32
    Välislingid
    0.31
    Activations Density 2.385%

    No Known Activations