Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7255
    Prev
    Next
    INDEX
    Explanations

    geographical locations and regions, often in relation to historical or cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.67
    oredCriteria
    -0.50
    WriteAttribute
    -0.49
     ligand
    -0.48
    aarrggbb
    -0.48
    raised
    -0.48
    matchCondition
    -0.48
     selectivity
    -0.47
     sitter
    -0.47
     selectors
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    0.41
    WithIOException
    0.39
     why
    0.39
     SqlCommand
    0.38
    principalTable
    0.38
     nakalista
    0.36
    ttemberg
    0.35
     jorden
    0.35
     auraient
    0.34
     coû
    0.33
    Activations Density 0.678%

    No Known Activations