© 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. 0-GEMMASCOPE-RES-16K
    11. 2525
    Prev
    Next
    INDEX
    Explanations

    terms related to velocity and correlations in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     char
    -0.75
     bot
    -0.70
     band
    -0.68
     piece
    -0.68
     bri
    -0.66
     app
    -0.66
     pin
    -0.66
     magic
    -0.65
     bar
    -0.65
     chapter
    -0.65
    POSITIVE LOGITS
     edades
    0.76
     niebla
    0.75
     Infór
    0.73
     creencias
    0.70
     venganza
    0.69
     aislado
    0.69
     embarazada
    0.68
     avoient
    0.68
     asesinado
    0.68
     agujas
    0.68
    Activations Density 0.386%

    No Known Activations