© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110567
    Prev
    Next
    INDEX
    Explanations

    components related to structural elements and organization in written content

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

    sections, clauses, or phases

    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
    IntoConstraints
    -0.75
     CanadaChoose
    -0.73
     Roskov
    -0.72
    -------------</
    -0.72
     HasFactory
    -0.70
    WriteTagHelper
    -0.69
     <<<<<<<<<<<<<<
    -0.69
    Autoritní
    -0.68
    WithIOException
    -0.68
     Taktlose
    -0.68
    POSITIVE LOGITS
    echo
    0.39
    The
    0.37
    Through
    0.37
    Echo
    0.34
    A
    0.34
    Contact
    0.34
    мум
    0.34
    News
    0.33
    Amb
    0.33
    Sha
    0.33
    Activations Density 0.003%

    No Known Activations