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. 7-GEMMASCOPE-RES-16K
    6. 4513
    Prev
    Next
    INDEX
    Explanations

    specific chemical compounds and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QtWidgets
    -0.81
    endpush
    -0.70
     Occidente
    -0.66
     Baal
    -0.64
     symp
    -0.64
    ArgsConstructor
    -0.62
    RetentionPolicy
    -0.62
     Burroughs
    -0.61
     Horace
    -0.61
     Euph
    -0.60
    POSITIVE LOGITS
    GEBURTSDATUM
    1.01
     Pele
    0.78
    Kaieteur
    0.74
    onPage
    0.71
    ttes
    0.71
     CBE
    0.71
     Byrd
    0.71
    },[])
    0.70
    TypedDataSet
    0.70
     виправивши
    0.70
    Activations Density 1.814%

    No Known Activations