© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 6952
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to individuals, particularly "he," "his," and "she."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aig
    -0.67
     comod
    -0.64
     fora
    -0.61
    acd
    -0.61
     aspec
    -0.60
    setShow
    -0.60
     Vork
    -0.57
    ancia
    -0.56
     inva
    -0.56
     grosse
    -0.56
    POSITIVE LOGITS
     he
    1.63
     she
    1.52
    He
    1.51
     He
    1.50
    she
    1.40
    She
    1.35
     himself
    1.28
     She
    1.22
    himself
    1.21
     shes
    1.13
    Activations Density 0.287%

    No Known Activations