© 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. 677
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to biological or medical data and experimental procedures

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

    Tokens after capitalized words

    np_acts-logits-general · gemini-2.0-flash

    names and letters associated with entities

    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
    AnchorStyles
    -0.71
     ब्रेकडाउन
    -0.68
    RegressionTest
    -0.64
    TargetException
    -0.61
     Infórmanos
    -0.61
    toppers
    -0.60
    <unused51>
    -0.60
    <unused74>
    -0.60
    <unused42>
    -0.60
    <unused16>
    -0.60
    POSITIVE LOGITS
     above
    0.28
    Above
    0.27
     Utility
    0.27
    above
    0.26
    farwyddwr
    0.24
     Ouv
    0.23
     Util
    0.23
    vician
    0.23
     précédemment
    0.23
     Above
    0.23
    Activations Density 0.710%

    No Known Activations