© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 12576
    Prev
    Next
    INDEX
    Explanations

    references to geographical features, particularly parks and shores

    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
     ProtoMessage
    -0.88
    CloseOperation
    -0.83
    OGND
    -0.82
    хьтан
    -0.80
    MarshalTo
    -0.79
    roxene
    -0.77
    __':
    -0.77
     estekak
    -0.75
     onCancelled
    -0.75
    FileDescriptor
    -0.74
    POSITIVE LOGITS
     Shore
    0.83
     dam
    0.81
     shore
    0.77
     Dam
    0.72
    dam
    0.68
     cage
    0.68
    Dam
    0.67
    cage
    0.66
    Mob
    0.63
     Stud
    0.61
    Activations Density 0.621%

    No Known Activations