© 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. 15989
    Prev
    Next
    INDEX
    Explanations

    sections and keywords related to software licensing and warnings

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

    automatically generated code with warnings not to modify.

    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
    LookAnd
    -0.61
    CPtr
    -0.55
    səhifə
    -0.54
    AntiForgeryToken
    -0.52
    .*")]
    -0.51
    QMetaType
    -0.51
     arşivlendi
    -0.49
    ftagPool
    -0.49
    XmlAccessorType
    -0.48
    RetentionPolicy
    -0.47
    POSITIVE LOGITS
     generated
    1.33
    generated
    1.15
     Generated
    1.12
    Generated
    1.09
     GENERATED
    0.98
     generating
    0.96
    GENERATED
    0.94
     generator
    0.94
     Generating
    0.91
     generate
    0.90
    Activations Density 0.449%

    No Known Activations