© 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. 2-GEMMASCOPE-RES-16K
    6. 8829
    Prev
    Next
    INDEX
    Explanations

    references to tables and structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jo
    -0.34
    semantics
    -0.34
     Bs
    -0.34
    item
    -0.33
    Hi
    -0.33
     «
    -0.33
     п
    -0.32
     immer
    -0.32
     معم
    -0.31
     tal
    -0.31
    POSITIVE LOGITS
    ChildScrollView
    0.78
     المعيارى
    0.72
    adaptiveStyles
    0.66
     ProtoMessage
    0.65
    TypedDataSet
    0.64
    ViewImports
    0.63
     للمعارف
    0.60
     hombro
    0.59
    hombres
    0.59
     îna
    0.58
    Activations Density 0.172%

    No Known Activations