© 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. 169
    Prev
    Next
    INDEX
    Explanations

    technical details, references to figures and tables, and section labels in formal documents

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

    Mathematical or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    Let, Transform, W, Dex, don

    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
    AndEndTag
    -0.81
     contextLoads
    -0.68
    addCriterion
    -0.65
    WithIOException
    -0.60
    TintMode
    -0.58
    "}}>
    -0.57
    WriteTagHelper
    -0.56
    __).
    -0.55
    ValueStyle
    -0.54
    ')));
    -0.54
    POSITIVE LOGITS
     Recall
    0.63
     finito
    0.60
    stdc
    0.59
    Recall
    0.59
    Напомним
    0.57
    Datuak
    0.55
     We
    0.54
     motivates
    0.54
    μβρίου
    0.54
    Remark
    0.54
    Activations Density 0.339%

    No Known Activations