© 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. 3-GEMMASCOPE-RES-16K
    11. 8702
    Prev
    Next
    INDEX
    Explanations

    conjunctions and indicators of relationships in complex sentences

    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
     Bucure
    -0.66
     reaſon
    -0.62
     diſt
    -0.58
     AssemblyCulture
    -0.56
     purpoſe
    -0.53
     Diſ
    -0.53
     raiſ
    -0.52
     ſever
    -0.52
     anún
    -0.51
     Reſ
    -0.51
    POSITIVE LOGITS
    󠁿
    0.78
    EndContext
    0.76
    CJK
    0.74
     мәкал
    0.71
    <>();
    0.68
    endphp
    0.67
    Personensuche
    0.66
    MLLoader
    0.66
    <bos>
    0.66
    WRENCE
    0.62
    Activations Density 1.917%

    No Known Activations