© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8379
    Prev
    Next
    INDEX
    Explanations

    references to the name "Daniel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.77
     ModelExpression
    -0.76
    المكان
    -0.74
    RegressionTest
    -0.74
     ExecuteAsync
    -0.72
    GraphicsUnit
    -0.72
     comprom
    -0.71
    ClientSize
    -0.68
    })->
    -0.67
     Bede
    -0.66
    POSITIVE LOGITS
     charm
    0.72
     bait
    0.71
     Dar
    0.66
     Charm
    0.63
     buff
    0.61
    bait
    0.61
     charms
    0.55
    Charm
    0.55
    charming
    0.55
     aanbod
    0.53
    Activations Density 0.077%

    No Known Activations