Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12940
    Prev
    Next
    INDEX
    Explanations

    phrases related to identity verification and authentication processes

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

    Japanese particles

    np_acts-logits-general · gemini-2.0-flash

    処理, 死, 摂取, 事が

    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
    ようになった
    -0.54
     altro
    -0.53
     Dijo
    -0.53
    ėjimas
    -0.53
    ry
    -0.49
    t
    -0.49
    vian
    -0.48
    e
    -0.48
     kasarigan
    -0.48
    ėjimo
    -0.48
    POSITIVE LOGITS
    StandardCharsets
    0.71
     مرئيه
    0.67
    IntoConstraints
    0.60
    weł
    0.60
    SBATCH
    0.58
    도
    0.58
    ,
    0.56
    providedIn
    0.56
    yarnpkg
    0.55
    rachtet
    0.55
    Activations Density 0.043%

    No Known Activations