© 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. 8822
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences or emphasis on time-related phrases and actions

    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
    Another
    -0.47
    Additional
    -0.47
     Another
    -0.47
    Further
    -0.46
    今度は
    -0.45
     weitere
    -0.44
    Finally
    -0.43
    another
    -0.43
    finally
    -0.42
    further
    -0.42
    POSITIVE LOGITS
     ag
    1.27
     gain
    0.99
     agen
    0.98
     Ag
    0.95
    Ag
    0.90
    agin
    0.89
    gain
    0.87
     aga
    0.84
     AG
    0.82
     Aga
    0.82
    Activations Density 0.143%

    No Known Activations