© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9743
    Prev
    Next
    INDEX
    Explanations

    references to client-server interactions and API call structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.92
     ModelExpression
    -0.79
    цездатний
    -0.78
     kaarangay
    -0.74
    MessageOf
    -0.74
    NamedQueries
    -0.70
    encodeWith
    -0.70
    BufferException
    -0.70
     мәкал
    -0.69
     ویکی‌پدی
    -0.69
    POSITIVE LOGITS
    scriptcase
    1.73
    Pyx
    1.13
    chartInstance
    0.90
    nmgp
    0.75
    tinyos
    0.71
    Funciones
    0.55
    PYX
    0.53
    adaptiveStyles
    0.53
    codecSelfer
    0.52
     ldc
    0.51
    Activations Density 0.053%

    No Known Activations