© 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. 5364
    Prev
    Next
    INDEX
    Explanations

    JSON object structures and key-value pairs

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

    Code and/or error messages

    np_acts-logits-general · gemini-2.0-flash

    code configuration

    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
     Drapeau
    -0.60
     nostru
    -0.51
    rungsseite
    -0.50
     minutter
    -0.50
    ThemeOverlay
    -0.49
     aspetta
    -0.49
    faßt
    -0.49
     rarement
    -0.49
    moveToFirst
    -0.47
     actuels
    -0.47
    POSITIVE LOGITS
    apimachinery
    0.73
     etc
    0.73
     وتسجيلات
    0.64
    ~,
    0.63
    CodeAttribute
    0.61
    存于互联网档案馆
    0.59
    Hochspringen
    0.59
    ³,
    0.59
     XNUMX
    0.58
    ,​
    0.58
    Activations Density 0.060%

    No Known Activations