Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8104
    Prev
    Next
    INDEX
    Explanations

    references to the subject "he" and its variations in a text, focusing on male characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttemberg
    -0.42
    +#+
    -0.40
    providedIn
    -0.38
    Swatch
    -0.38
     Wiring
    -0.36
    msgTypes
    -0.35
    ntr
    -0.35
     rive
    -0.35
     Paro
    -0.35
     Fingerprint
    -0.34
    POSITIVE LOGITS
     Himself
    0.66
    She
    0.66
     himself
    0.62
    Him
    0.60
    hehe
    0.60
    himself
    0.58
    Mereka
    0.57
     Ellos
    0.57
    He
    0.57
    she
    0.57
    Activations Density 0.249%

    No Known Activations