© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9011
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

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

    Fractions or division

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and equations

    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
    msgTypes
    -0.70
    IntoConstraints
    -0.69
    DoubleQuotes
    -0.63
     Chwiliwch
    -0.61
    errHandler
    -0.57
     IBOutlet
    -0.56
    httphttps
    -0.54
    extAlignment
    -0.51
    ModelSerializer
    -0.51
    TagHelper
    -0.51
    POSITIVE LOGITS
     norvég
    0.38
    Autoritní
    0.32
     '{@
    0.31
     Resultados
    0.30
     elef
    0.28
    sieger
    0.28
     vectorielles
    0.28
    ']>
    0.27
    TintMode
    0.27
     Inſ
    0.26
    Activations Density 2.015%

    No Known Activations