© 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. 20-GEMMASCOPE-RES-131K
    11. 31746
    Prev
    Next
    INDEX
    Explanations

    references to specific architecture and design entities or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.66
     للاسماء
    -0.65
    XmlAccessType
    -0.61
    ScopeManager
    -0.58
    CppMethod
    -0.57
    mtrl
    -0.57
    astify
    -0.56
     dieſer
    -0.55
     ſind
    -0.53
     resourceCulture
    -0.53
    POSITIVE LOGITS
     planning
    0.54
     architectural
    0.51
     engineering
    0.49
     pembangunan
    0.49
     architect
    0.47
     engineer
    0.47
     engineers
    0.47
     construction
    0.47
     arquite
    0.46
    Architect
    0.45
    Activations Density 0.019%

    No Known Activations