Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14557
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals involved in a community or industry context

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

    Appears in magazine/publication context

    np_acts-logits-general · gemini-2.0-flash

    magazine, Analysts, data

    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
     purpoſe
    -0.45
     pleaſure
    -0.42
     médicaux
    -0.39
     ſtand
    -0.38
    WireFormatLite
    -0.38
     ſt
    -0.36
     surfact
    -0.36
     psychi
    -0.35
     reaſon
    -0.35
     thérape
    -0.35
    POSITIVE LOGITS
    xase
    0.46
     Spitze
    0.45
    oderma
    0.44
    setopt
    0.43
    lexikon
    0.43
     مواليد
    0.41
    ⓧ
    0.41
     pinulongan
    0.41
     kasarigan
    0.41
     createSprite
    0.40
    Activations Density 0.301%

    No Known Activations