© 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. 38383
    Prev
    Next
    INDEX
    Explanations

    references to actions and processes related to organization and manipulation

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

    out or away

    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
    HasAnnotation
    -0.48
    ://$
    -0.44
    SizeMode
    -0.40
    ]=>
    -0.36
    CGRectMake
    -0.35
    
    -0.34
    енча
    -0.34
    InstrumentedTest
    -0.33
     生命周期
    -0.33
     ModelExpression
    -0.33
    POSITIVE LOGITS
     up
    1.34
     out
    1.22
     away
    1.14
     down
    1.13
     off
    0.95
     forth
    0.95
    away
    0.79
     indietro
    0.75
    down
    0.74
    up
    0.72
    Activations Density 0.384%

    No Known Activations