© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 676
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and their associated forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    occurrences of the word "she" and its variants in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    pronoun + body part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.84
     chi̍t
    -0.66
     تانيه
    -0.63
    fromnode
    -0.61
     ExecuteAsync
    -0.59
     onCancelled
    -0.58
    AntiForgeryToken
    -0.57
     insuffisamment
    -0.56
     Seeder
    -0.54
     المعيارى
    -0.53
    POSITIVE LOGITS
     eyes
    1.01
     fingers
    0.81
     brows
    0.73
     eyebrows
    0.73
     lips
    0.73
     cheeks
    0.70
     brow
    0.70
    eyes
    0.70
     heart
    0.69
     mood
    0.68
    Activations Density 0.035%

    No Known Activations