© 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. 10-GEMMASCOPE-RES-16K
    6. 13497
    Prev
    Next
    INDEX
    Explanations

    specific compounds and materials related to scientific and engineering contexts, particularly in relation to growth factors, fuel formulations, and medical compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    suff
    -0.65
     Refin
    -0.61
    Slf
    -0.60
    DIRE
    -0.60
    LARE
    -0.59
    âmara
    -0.59
     שוליים
    -0.58
    loroethane
    -0.58
     Sulf
    -0.58
    approche
    -0.57
    POSITIVE LOGITS
    <bos>
    0.85
    errHandler
    0.61
    tvguidetime
    0.45
    ContentAsync
    0.45
    brainly
    0.45
    protoimpl
    0.44
     برانيه
    0.42
    KURZBESCHREIBUNG
    0.41
    hbar
    0.40
    wise
    0.38
    Activations Density 1.194%

    No Known Activations