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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 5334
    Prev
    Next
    INDEX
    Explanations

    complex sentences with multiple clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.34
    PageRoute
    -0.32
    nestjs
    -0.32
    ộp
    -0.30
    ="@+
    -0.29
    vaadin
    -0.29
    astify
    -0.28
     Subsequent
    -0.27
     anum
    -0.27
     subsequent
    -0.26
    POSITIVE LOGITS
     finally
    4.66
     Finally
    4.06
    finally
    4.06
    Finally
    4.03
     finalmente
    3.78
     enfin
    3.75
     наконец
    3.64
     FINALLY
    3.44
     Finalmente
    3.39
    Finalmente
    3.31
    Activations Density 1.165%

    No Known Activations