© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6118
    Prev
    Next
    INDEX
    Explanations

    items related to user interface elements or layout specifications

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

    Code snippets and identifiers

    np_acts-logits-general · gemini-2.0-flash

    inhibiting effect, type ids, CC="$

    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
    MigrationBuilder
    -0.69
    rungsseite
    -0.63
    RenderAtEndOf
    -0.62
     Monfieur
    -0.60
    :✨
    -0.59
    IntoConstraints
    -0.59
     Formosa
    -0.59
    AndEndTag
    -0.58
    InputBorder
    -0.57
    TextHelper
    -0.55
    POSITIVE LOGITS
    JNIEnv
    0.57
    spli
    0.56
     Rates
    0.50
     makeStyles
    0.50
    Geplaatst
    0.49
     rates
    0.48
    Населення
    0.48
    gameserver
    0.47
     AutoMapper
    0.47
     mapStateToProps
    0.46
    Activations Density 0.028%

    No Known Activations