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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15051
    Prev
    Next
    INDEX
    Explanations

    references to specific people or well-known individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.82
    MessageOf
    -0.72
     gynhyrchwyd
    -0.69
    ValueStyle
    -0.69
    PerformLayout
    -0.63
     насељу
    -0.63
     InputDecoration
    -0.62
    DoubleQuotes
    -0.58
    migrationBuilder
    -0.58
     Monfieur
    -0.58
    POSITIVE LOGITS
     said
    0.75
     wrote
    0.64
     (@
    0.62
     replied
    0.57
     Posts
    0.56
     yesterday
    0.55
     says
    0.54
     dijo
    0.52
     Wrote
    0.48
     detto
    0.48
    Activations Density 0.197%

    No Known Activations