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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 7175
    Prev
    Next
    INDEX
    Explanations

    formatting-related elements in code or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.64
    Datuak
    -0.63
    __*/
    -0.61
    ropractic
    -0.61
     يتيمه
    -0.59
    PyExc
    -0.59
    yorsunuz
    -0.57
     wireType
    -0.57
     déploy
    -0.56
    SerializedName
    -0.55
    POSITIVE LOGITS
    äsident
    0.49
    CopyWith
    0.49
     Schlaf
    0.46
     Wicidata
    0.45
     Retry
    0.44
    NotEqualTo
    0.44
    binaan
    0.44
     createState
    0.43
     Εκ
    0.42
    өз
    0.42
    Activations Density 0.053%

    No Known Activations