© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 42134
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and ethical concepts

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

    information, faculty, RNA, factors, trial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     including
    -1.48
     Including
    -1.41
    Including
    -1.32
    包括
    -1.27
    including
    -1.27
     INCLUDING
    -1.24
     include
    -1.17
     כולל
    -1.16
     incluindo
    -1.16
     includes
    -1.12
    POSITIVE LOGITS
     ones
    0.42
     sekal
    0.41
     כא
    0.36
    цездатний
    0.35
    agaimana
    0.34
     celles
    0.34
    aspectRatio
    0.34
    PostConstruct
    0.33
    EndContext
    0.32
     teş
    0.31
    Activations Density 0.049%

    No Known Activations