© 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. 17-GEMMASCOPE-RES-16K
    6. 6879
    Prev
    Next
    INDEX
    Explanations

    technical terms and function calls related to programming or data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.86
    󠁿
    -0.84
    Rujuakan
    -0.82
    rawDesc
    -0.79
     تضيفلها
    -0.73
    ाहरण
    -0.70
     мәкал
    -0.69
     Roskov
    -0.68
     كومونز
    -0.68
     }}"></
    -0.67
    POSITIVE LOGITS
    NoSuchAlgorithm
    0.57
     gynhyrchwyd
    0.57
    UserScript
    0.56
     endogenous
    0.54
    lapsingToolbar
    0.52
     BoxDecoration
    0.51
    צלחה
    0.46
     Johansen
    0.45
     Chriftian
    0.44
    providedIn
    0.43
    Activations Density 1.029%

    No Known Activations