© 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. 22-GEMMASCOPE-RES-16K
    11. 10727
    Prev
    Next
    INDEX
    Explanations

    code-related structures or elements

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

    Code or expressions with parentheses, brackets, semicolons

    np_acts-logits-general · gemini-2.0-flash

    code snippets and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abestanden
    -0.74
     disambiguazione
    -0.73
     تانيه
    -0.66
    +#+#
    -0.64
     podjela
    -0.64
    AutoScaleMode
    -0.62
    principalColumn
    -0.62
    NewUrlParser
    -0.62
     étoient
    -0.60
    Sucesor
    -0.60
    POSITIVE LOGITS
    azo
    0.53
    etcode
    0.50
    доступ
    0.43
     tids
    0.43
    åringen
    0.42
    rvats
    0.41
    ULA
    0.41
    uminense
    0.41
     préférences
    0.41
    mě
    0.41
    Activations Density 0.023%

    No Known Activations