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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5566
    Prev
    Next
    INDEX
    Explanations

    references to crime dramas, movies, and pop culture related to fiction and reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.47
     dimin
    -0.33
    แผ
    -0.32
    AutoSize
    -0.32
     kwiaty
    -0.31
    Sklici
    -0.31
    mitos
    -0.30
     vitales
    -0.29
    Mercy
    -0.29
     Converting
    -0.29
    POSITIVE LOGITS
     movie
    0.57
     Hollywood
    0.56
     film
    0.56
     fictional
    0.56
    出版年
    0.54
    parametrize
    0.51
     movies
    0.49
    withIdentifier
    0.49
     filme
    0.49
     filmu
    0.48
    Activations Density 0.483%

    No Known Activations