© 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. 27-GEMMASCOPE-RES-16K
    11. 11148
    Prev
    Next
    INDEX
    Explanations

    terms related to cinema and its technical aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gră
    -0.56
    väg
    -0.54
    ../../../
    -0.49
    >{@
    -0.48
     referrerpolicy
    -0.47
    Sklici
    -0.47
    epa
    -0.45
     purpoſe
    -0.45
     كورة
    -0.45
     ſche
    -0.45
    POSITIVE LOGITS
    in
    0.68
    ini
    0.67
    ins
    0.65
    ining
    0.64
    inx
    0.63
    IN
    0.61
    iny
    0.60
    inal
    0.60
    ina
    0.59
    inn
    0.58
    Activations Density 0.824%

    No Known Activations