© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7466
    Prev
    Next
    INDEX
    Explanations

    references to the subject pronoun "he" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.78
    estrian
    -0.69
    󠁮
    -0.68
     waisted
    -0.67
    woody
    -0.66
    romechanical
    -0.65
    <unused76>
    -0.64
    <unused43>
    -0.64
    <pad>
    -0.64
     dressings
    -0.63
    POSITIVE LOGITS
     ik
    0.56
     homicidio
    0.38
    tek
    0.38
    løs
    0.38
    Chat
    0.38
     volcán
    0.37
     marbre
    0.37
     Ik
    0.36
     Chat
    0.36
     consideración
    0.36
    Activations Density 0.477%

    No Known Activations