© 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. 9757
    Prev
    Next
    INDEX
    Explanations

    specific terms and identifiers related to code structure and properties in programming contexts

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

    numerical values and identifiers in technical documentation and code configuration files.

    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
    PYX
    -0.52
    󠁣
    -0.51
    RefNanny
    -0.50
    yntaxException
    -0.50
     >=",
    -0.49
     imageNamed
    -0.45
    UrlResolution
    -0.45
    /**
    -0.43
     ویکی‌پدیای
    -0.42
     firebaseConfig
    -0.41
    POSITIVE LOGITS
    _
    0.96
    ・
    0.56
    \_
    0.49
     _
    0.49
    ——
    0.43
    ـ
    0.42
    sidemargin
    0.41
     –
    0.40
    —
    0.40
     -
    0.40
    Activations Density 0.757%

    No Known Activations