© 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. 31-GEMMASCOPE-RES-16K
    11. 8949
    Prev
    Next
    INDEX
    Explanations

    occurrences of function definitions and related syntax in code

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

    function declarations and callback function parameters 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
    󠁴
    -0.59
    hilangan
    -0.54
     المعيارى
    -0.49
     EconPapers
    -0.48
    Abit
    -0.45
    SBATCH
    -0.45
    OrNil
    -0.43
    Alerter
    -0.43
    Хьажоргаш
    -0.43
     magasiner
    -0.43
    POSITIVE LOGITS
    TokenNameCOMMA
    0.60
     שוליים
    0.56
    oneofs
    0.43
     purpoſe
    0.42
    NewLabel
    0.42
    QMetaType
    0.42
    hogy
    0.42
    endregion
    0.40
    ,)
    0.39
     اینکه
    0.36
    Activations Density 0.709%

    No Known Activations