© 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. 15-GEMMASCOPE-RES-16K
    11. 12628
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.89
     LoggerFactory
    -0.80
    ArrowToggle
    -0.79
    GraphicsUnit
    -0.76
    +#+#
    -0.72
    UnusedPrivate
    -0.70
    RenderAtEndOf
    -0.70
    AccessFile
    -0.69
     unknownFields
    -0.68
    NameInMap
    -0.67
    POSITIVE LOGITS
     właśnie
    0.72
     právě
    0.68
     appunto
    0.53
     yours
    0.53
    正好
    0.51
    今回の
    0.47
     eben
    0.44
     ours
    0.43
     оригіналу
    0.42
     jij
    0.42
    Activations Density 0.851%

    No Known Activations