© 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. 9-GEMMASCOPE-RES-16K
    11. 7052
    Prev
    Next
    INDEX
    Explanations

    phrases indicating casting and roles in film or theater

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.56
    
    -0.51
     ProtoMessage
    -0.48
    发表于
    -0.48
    LabelTagHelper
    -0.47
    AutoScaleMode
    -0.46
    .*")]
    -0.45
    getActiveSheet
    -0.44
    expandindo
    -0.42
    WillAppear
    -0.42
    POSITIVE LOGITS
     portraying
    0.56
     portrayal
    0.55
    Character
    0.54
     portrayed
    0.52
     roles
    0.52
    扮演
    0.52
     Character
    0.51
     role
    0.51
    character
    0.51
     character
    0.50
    Activations Density 0.129%

    No Known Activations