© 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. 552
    Prev
    Next
    INDEX
    Explanations

    structured data representation such as code or mathematical expressions

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

    The number 1

    np_acts-logits-general · gemini-2.0-flash

    a number followed by a letter or period

    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
    RenderAtEndOf
    -0.63
    TagMode
    -0.58
     disambiguazione
    -0.56
    DockStyle
    -0.50
    ConstraintMaker
    -0.50
     iconLine
    -0.47
    CloseOperation
    -0.46
    存于互联网档案馆
    -0.45
    PyExc
    -0.45
    addGap
    -0.44
    POSITIVE LOGITS
     First
    0.47
    getFirst
    0.46
    первых
    0.42
    First
    0.42
     isFirst
    0.40
     getFirst
    0.39
    ()]);
    0.39
    >`;
    0.38
     Primo
    0.37
    ariConfig
    0.37
    Activations Density 1.753%

    No Known Activations