Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 7621
    Prev
    Next
    INDEX
    Explanations

    mentions of location or geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.88
     jspb
    -0.75
     diarios
    -0.71
    XMLSchema
    -0.71
    Datuak
    -0.69
    FieldBuilder
    -0.68
    WebServlet
    -0.68
    ]^{-
    -0.68
     mAdapter
    -0.67
    MigrationBuilder
    -0.66
    POSITIVE LOGITS
     location
    3.10
     Location
    2.72
    location
    2.69
     locations
    2.68
     LOCATION
    2.56
    Location
    2.54
     Locations
    2.47
    locations
    2.37
    LOCATION
    2.30
    Locations
    2.23
    Activations Density 0.059%

    No Known Activations