© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 6072
    Prev
    Next
    INDEX
    Explanations

    statements of existence or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.95
    XmlAccessType
    -0.66
    انتهای
    -0.61
    expandindo
    -0.59
    WebElementEntity
    -0.56
    aarrggbb
    -0.56
    MigrationBuilder
    -0.56
    UNGE
    -0.54
    anglès
    -0.52
    évaluateur
    -0.52
    POSITIVE LOGITS
     reflected
    1.37
     evidenced
    0.99
     exemplified
    0.92
     why
    0.91
     mirrored
    0.91
     evident
    0.87
     illustrated
    0.85
     aided
    0.78
     partly
    0.78
     testified
    0.77
    Activations Density 0.446%

    No Known Activations