© 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 EvalsExportsAPI 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. 14997
    Prev
    Next
    INDEX
    Explanations

    instances of high crowd density or overwhelming situations

    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
    hiran
    -0.44
    pinMode
    -0.42
    fortunes
    -0.38
    knex
    -0.36
     piecewise
    -0.35
    ˹
    -0.34
     neuter
    -0.34
     knex
    -0.33
    得罪
    -0.33
    DataContract
    -0.33
    POSITIVE LOGITS
     crowd
    2.52
     crowds
    2.48
     crowded
    2.36
    crowd
    2.16
    crow
    2.09
     crowding
    2.06
     CROW
    2.03
     Crowd
    1.96
    Crowd
    1.96
    Crow
    1.90
    Activations Density 0.327%

    No Known Activations