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. 19-GEMMASCOPE-RES-16K
    6. 11307
    Prev
    Next
    INDEX
    Explanations

    transportation-related actions and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.55
     continúas
    -0.55
     كومونز
    -0.53
    TagMode
    -0.53
     AssemblyCulture
    -0.51
    errHandler
    -0.49
    NameInMap
    -0.49
    ScopeManager
    -0.47
    fjspx
    -0.47
    lapsingToolbar
    -0.46
    POSITIVE LOGITS
     menuju
    1.11
     hacia
    1.07
     naar
    1.06
     reaching
    0.91
     from
    0.87
     towards
    0.87
     toward
    0.85
     reach
    0.83
     thither
    0.81
    Reaching
    0.81
    Activations Density 0.459%

    No Known Activations