© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8071
    Prev
    Next
    INDEX
    Explanations

    instances of data type definitions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    author
    -0.42
    "}"
    -0.41
    </b>
    -0.37
    s
    -0.37
    <thead>
    -0.35
    </sup>
    -0.35
    fo
    -0.34
     poles
    -0.34
    a
    -0.34
    </i>
    -0.34
    POSITIVE LOGITS
    uint
    3.48
     uint
    3.44
     UInt
    1.59
    Uint
    1.52
    UInt
    1.48
    UINT
    1.38
     UINT
    1.37
     Uint
    1.27
    stdint
    1.12
     ulong
    1.05
    Activations Density 0.095%

    No Known Activations