© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2047
    Prev
    Next
    INDEX
    Explanations

    patterns associated with numbers and symbols, particularly in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Myers
    -0.49
     Home
    -0.49
     home
    -0.47
     Mú
    -0.47
     Kem
    -0.46
    来自
    -0.46
     समीक्षाएं
    -0.46
     أما
    -0.45
    خول
    -0.45
     pre
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.85
    migrationBuilder
    0.83
    TagMode
    0.78
    +:+
    0.76
    DoubleQuotes
    0.72
    tvguidetime
    0.70
     JpaRepository
    0.68
     Cæsar
    0.65
    principalColumn
    0.64
    principalTable
    0.63
    Activations Density 0.551%

    No Known Activations