© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9607
    Prev
    Next
    INDEX
    Explanations

    assignments and comparisons in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numeric literals and assignment operators in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.89
    OGND
    -0.89
    SourceChecksum
    -0.86
    Tembelea
    -0.78
    ftagPool
    -0.78
    〮
    -0.77
    haikusbot
    -0.76
    Personendaten
    -0.75
     estekak
    -0.75
     ModelExpression
    -0.75
    POSITIVE LOGITS
     
    0.71
    1
    0.67
    2
    0.66
    3
    0.59
    4
    0.57
    5
    0.56
    0
    0.54
    7
    0.50
    6
    0.50
    9
    0.49
    Activations Density 1.801%

    No Known Activations