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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12535
    Prev
    Next
    INDEX
    Explanations

    evidence and factors related to legal and evaluative criteria in documents

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

    uncertainty or refutation

    np_acts-logits-general · gemini-2.0-flash

    not important or relevant

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     flex
    -0.29
     named
    -0.26
     Skill
    -0.26
     said
    -0.26
     Method
    -0.25
     VERB
    -0.25
     ahead
    -0.25
     paž
    -0.25
    ereich
    -0.25
    flex
    -0.25
    POSITIVE LOGITS
    ThroughAttribute
    0.75
    ніципалі
    0.69
     transfieras
    0.69
    :✨
    0.66
     Picchu
    0.66
     AssemblyCulture
    0.65
    цезда
    0.65
    webElement
    0.63
     increí
    0.60
    yntaxException
    0.60
    Activations Density 0.786%

    No Known Activations