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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2786
    Prev
    Next
    INDEX
    Explanations

    occurrences of the beginning of a document or section headers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.71
    StatusOK
    -0.68
    最快更新
    -0.68
    OneToMany
    -0.63
    rasta
    -0.57
     kanya
    -0.57
    ropriate
    -0.57
    yra
    -0.57
    Priest
    -0.55
     vPvB
    -0.55
    POSITIVE LOGITS
     وتسجيلات
    0.81
     intptr
    0.70
     uParam
    0.70
    BeginContext
    0.60
    IntoConstraints
    0.59
     bParam
    0.58
    WEBPACK
    0.58
     iParam
    0.57
    Personendaten
    0.56
    허
    0.56
    Activations Density 0.020%

    No Known Activations