© 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. 8765
    Prev
    Next
    INDEX
    Explanations

    Java comments and error handling scenarios

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

    comments that explain code logic or provide instructions.

    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
     ModelExpression
    -0.74
    AccessorTable
    -0.60
    parsedMessage
    -0.58
     CreateTagHelper
    -0.56
     Италијани
    -0.54
    HasAnnotation
    -0.54
     EconPapers
    -0.52
    ChildScrollView
    -0.52
    parency
    -0.52
     GenerationType
    -0.50
    POSITIVE LOGITS
     proceed
    0.55
     demek
    0.54
     nothing
    0.54
    说明
    0.52
     indicates
    0.52
     indicating
    0.49
     berarti
    0.48
     means
    0.48
    nothing
    0.47
     no
    0.46
    Activations Density 0.464%

    No Known Activations