© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14642
    Prev
    Next
    INDEX
    Explanations

    high-frequency technical terms or function names in code

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

    Code, assembly, or identifiers

    np_acts-logits-general · gemini-2.0-flash

    all laid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    tų
    -0.53
    tingham
    -0.52
    sky
    -0.51
     Goodwin
    -0.47
     viv
    -0.47
    WritableDatabase
    -0.47
    ahara
    -0.47
    LING
    -0.47
     zuk
    -0.46
     Lip
    -0.45
    POSITIVE LOGITS
    tvguidetime
    0.80
    Diweddarwch
    0.78
     Administrativna
    0.77
    tagHelperRunner
    0.74
    SequentialGroup
    0.72
    EndProject
    0.68
    Personensuche
    0.67
    EndGlobalSection
    0.67
    featureID
    0.65
    Искәрмәләр
    0.65
    Activations Density 0.040%

    No Known Activations