© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8891
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to healthcare or medical research

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

    Follows prepositions "in" or "at"

    np_acts-logits-general · gemini-2.0-flash

    words following prepositions or proper nouns

    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
    SharedCtor
    -0.76
    transQ
    -0.68
    #+#
    -0.67
    featureID
    -0.66
     ddelweddau
    -0.65
     الحره
    -0.64
     كومونز
    -0.64
    aarrggbb
    -0.63
    новниш
    -0.63
    Източници
    -0.63
    POSITIVE LOGITS
    FontStyle
    0.60
     Frat
    0.54
    )(((
    0.50
    Font
    0.48
    lique
    0.46
     Font
    0.45
    Frat
    0.45
     Sì
    0.44
    وارد
    0.44
    Sharp
    0.44
    Activations Density 0.005%

    No Known Activations