© 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. 34-GEMMASCOPE-RES-16K
    11. 4510
    Prev
    Next
    INDEX
    Explanations

    references to popular comic book characters and franchises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Macedonian
    -0.35
     tarik
    -0.34
    mbggenerated
    -0.33
     pancre
    -0.32
     surfact
    -0.31
    FormUrlEncoded
    -0.30
     Iowa
    -0.29
    胰
    -0.29
     ObjectMapper
    -0.29
     lowa
    -0.29
    POSITIVE LOGITS
     Batman
    1.01
    Batman
    0.98
     Bat
    0.93
     Gotham
    0.92
     batman
    0.92
    Bat
    0.90
     BAT
    0.88
     bat
    0.88
     Joker
    0.87
    batman
    0.87
    Activations Density 0.147%

    No Known Activations