© 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. 3514
    Prev
    Next
    INDEX
    Explanations

    elements related to properties and characteristics of materials

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

    descriptions of positive attributes or desirable characteristics of objects, systems, or concepts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    phrases describing beneficial or desirable properties or characteristics.

    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
    msgTypes
    -0.60
     ModelExpression
    -0.56
    RTLR
    -0.55
     wireType
    -0.54
    wapV
    -0.53
    ChildIndex
    -0.50
     TextInputType
    -0.50
    InSection
    -0.50
    IVEREF
    -0.50
     utafitiHapana
    -0.49
    POSITIVE LOGITS
     characteristics
    2.05
    characteristics
    1.78
     attributes
    1.72
     Characteristics
    1.71
     traits
    1.70
     Eigenschaften
    1.70
     qualities
    1.68
    Characteristics
    1.63
     properties
    1.57
     características
    1.55
    Activations Density 0.962%

    No Known Activations