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. 10402
    Prev
    Next
    INDEX
    Explanations

    technical terminology and specific identifiers related to systems or entities

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

    Preceding conjunction "and"

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and compound phrases

    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
     nahilalakip
    -0.91
    expandindo
    -0.85
    windowFixed
    -0.81
    protoimpl
    -0.77
    XmlAccessorType
    -0.75
     متعلقه
    -0.74
     disambiguazione
    -0.72
     Italijanski
    -0.72
    évaluateur
    -0.71
    UAWEI
    -0.71
    POSITIVE LOGITS
    And
    1.65
     And
    1.65
    and
    1.41
    AND
    1.03
     AND
    1.02
     and
    1.01
    和
    0.89
    ands
    0.85
    アンド
    0.74
    anda
    0.74
    Activations Density 0.149%

    No Known Activations