© 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. 2-GEMMASCOPE-RES-16K
    11. 7182
    Prev
    Next
    INDEX
    Explanations

    references to movies and cinema

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.38
    ().__
    -0.37
    Šaltiniai
    -0.35
    preventDefault
    -0.34
    anças
    -0.34
     desnuda
    -0.34
    sumi
    -0.33
    Dermott
    -0.33
     grasses
    -0.33
    Confused
    -0.33
    POSITIVE LOGITS
     movie
    3.77
     Movie
    3.28
    movie
    3.27
    Movie
    3.19
     movies
    3.17
     MOVIE
    3.05
     Movies
    2.81
    movies
    2.69
    Movies
    2.63
    MOVIE
    2.59
    Activations Density 0.108%

    No Known Activations