© 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. 1-GEMMASCOPE-RES-16K
    6. 8722
    Prev
    Next
    INDEX
    Explanations

    occurrences of whitespace or special formatting characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.31
    StructEnd
    -0.29
    toThrow
    -0.24
    MessageOf
    -0.23
     embalaje
    -0.22
     présidenti
    -0.21
     inscripción
    -0.21
    ècie
    -0.21
     fiscales
    -0.20
     انگلیسی
    -0.19
    POSITIVE LOGITS
     nonUne
    0.69
     Janice
    0.62
    aaron
    0.60
     كومونز
    0.60
     MainAxisSize
    0.59
    Ranks
    0.59
     Portions
    0.59
    ♲
    0.58
     encomp
    0.57
    ğından
    0.57
    Activations Density 0.169%

    No Known Activations