© 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. 24-GEMMASCOPE-RES-16K
    6. 15871
    Prev
    Next
    INDEX
    Explanations

    references to specific plant and insect species

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

    before suffixes

    np_acts-logits-general · gemini-2.0-flash

    female gendered noun suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     him
    -0.89
     himself
    -0.75
    him
    -0.72
    彼は
    -0.71
     duquel
    -0.71
     Celui
    -0.66
     który
    -0.66
     themselves
    -0.66
    ômico
    -0.65
     Himself
    -0.63
    POSITIVE LOGITS
     she
    0.98
     celle
    0.84
    she
    0.75
     Celle
    0.73
    She
    0.70
    彼女
    0.68
     She
    0.67
     mistress
    0.64
    彼女の
    0.64
    녀
    0.63
    Activations Density 0.064%

    No Known Activations