© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 528
    Prev
    Next
    INDEX
    Explanations

    contexts related to technical or procedural assessments

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

    Following "Under" or a number/integer

    np_acts-logits-general · gemini-2.0-flash

    phrases introducing conditions or terms

    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
     naselje
    -0.33
     artística
    -0.33
     persino
    -0.33
    forestation
    -0.32
    ITURE
    -0.32
    saraba
    -0.32
     newOwner
    -0.32
     ARTISTS
    -0.31
     DEFENDANT
    -0.31
     متعلقه
    -0.31
    POSITIVE LOGITS
     EconPapers
    0.58
    uxxxx
    0.54
    ISupport
    0.54
    SequentialGroup
    0.53
     defaultstate
    0.52
    UnusedPrivate
    0.52
     arşivlendi
    0.51
     ExecuteAsync
    0.50
     ModelExpression
    0.49
    ngths
    0.49
    Activations Density 0.912%

    No Known Activations