© 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. 94842
    Prev
    Next
    INDEX
    Explanations

    unit measures, specifically focusing on volume, weight, and density metrics used in scientific contexts

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

    units followed by exponents

    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
     grü
    -0.34
     createSlice
    -0.33
    peak
    -0.33
     speci
    -0.33
    燙
    -0.30
    itself
    -0.30
     Volkes
    -0.30
    generally
    -0.29
     beſ
    -0.29
    alnız
    -0.29
    POSITIVE LOGITS
    CDCl
    0.90
    RegistryLite
    0.65
     BorderRadius
    0.64
     estekak
    0.64
    LLocation
    0.63
     MainAxisSize
    0.63
    DockStyle
    0.60
     transfieras
    0.59
     RIPRODUZIONE
    0.58
    vccd
    0.57
    Activations Density 0.045%

    No Known Activations