© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9122
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to programming and mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erweise
    -0.40
     protoimpl
    -0.36
     Obrador
    -0.33
    ไม
    -0.32
     المعيارى
    -0.31
    estimm
    -0.31
    さっき
    -0.30
     createState
    -0.29
    zweck
    -0.29
    AnchorStyles
    -0.29
    POSITIVE LOGITS
    RenderAtEndOf
    0.77
    :✨
    0.61
     BoxFit
    0.60
    InvalidProtocol
    0.58
     تضيفلها
    0.57
    WriteBarrier
    0.56
    ⓧ
    0.56
    NameInMap
    0.55
    LookAnd
    0.53
    tagHelperRunner
    0.52
    Activations Density 0.539%

    No Known Activations