© 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. 18-GEMMASCOPE-RES-16K
    11. 854
    Prev
    Next
    INDEX
    Explanations

    capitalized proper nouns and keywords typically associated with names or significant terms

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

    after capitalized words

    np_acts-logits-general · gemini-2.0-flash

    Wellesley, Timber, Trujillo, Ade, pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rhestr
    -0.63
     '*')
    -0.56
    "";
    -0.54
    "،
    -0.53
    yaitu
    -0.52
    ]='\
    -0.52
    .}\
    -0.48
    ."]
    -0.48
    ."</
    -0.48
     IDisposable
    -0.48
    POSITIVE LOGITS
    ItemBackground
    0.67
     الاطلاع
    0.64
    InjectAttribute
    0.62
    Diwedd
    0.59
    unknownFields
    0.57
    ngdoc
    0.57
    BufferException
    0.54
    帖最后由
    0.54
    basicConfig
    0.54
    setParent
    0.53
    Activations Density 0.530%

    No Known Activations