© 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. 121850
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and concepts, particularly those associated with state management and parameters in AngularJS

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

    retrieving parameters or extras

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     >=",
    -0.74
    
    -0.69
     <=",
    -0.65
     فريبيس
    -0.63
     snippetHide
    -0.63
    发表于
    -0.62
     defaultstate
    -0.60
    MigrationBuilder
    -0.59
     MainAxisSize
    -0.58
    ])){
    -0.56
    POSITIVE LOGITS
    Params
    0.63
    getExtras
    0.52
     params
    0.47
     Params
    0.47
     ActivatedRoute
    0.45
    params
    0.43
     getIntent
    0.43
    Parms
    0.42
     getArguments
    0.40
    arguments
    0.39
    Activations Density 0.002%

    No Known Activations