© 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. 410
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages, specifically Java and libraries associated with it

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

    Code, file paths, and class names

    np_acts-logits-general · gemini-2.0-flash

    commons math class names

    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
     Sünde
    -0.31
     peito
    -0.30
    Personendaten
    -0.28
     Juifs
    -0.27
     póź
    -0.26
     Bemerkungen
    -0.26
    <strong>
    -0.25
     Infór
    -0.25
     enggak
    -0.25
     Verpflichtung
    -0.25
    POSITIVE LOGITS
    WithIOException
    0.81
     дописавши
    0.67
     invokingState
    0.60
     queſta
    0.59
     genres
    0.59
     queſto
    0.59
    oredCriteria
    0.59
    <unused41>
    0.59
    [@BOS@]
    0.58
    <unused8>
    0.58
    Activations Density 0.743%

    No Known Activations