© 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. 22-GEMMASCOPE-RES-16K
    6. 3497
    Prev
    Next
    INDEX
    Explanations

    references to personal health and medical conditions

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

    Followed by female pronouns

    np_acts-logits-general · gemini-2.0-flash

    female pronouns she her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     яке
    -0.78
    ньому
    -0.74
    quels
    -0.69
     ambao
    -0.69
     Оно
    -0.68
     которое
    -0.67
     dets
    -0.65
     οποίο
    -0.63
     Akismet
    -0.63
     cherchés
    -0.63
    POSITIVE LOGITS
     her
    4.25
     she
    4.15
     herself
    3.43
    she
    3.00
     그녀
    2.74
     hers
    2.69
    她
    2.68
    彼女の
    2.68
    She
    2.63
    herself
    2.63
    Activations Density 2.704%

    No Known Activations