Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12290
    Prev
    Next
    INDEX
    Explanations

    specific terms related to medical conditions and anatomical references

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

    females and girls

    np_acts-logits-general · gemini-2.0-flash

    girls and female

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    copyWith
    -0.79
    tagHelperRunner
    -0.79
    ⓧ
    -0.77
    httphttps
    -0.74
    المناصب
    -0.74
     Потому
    -0.72
     bodyParser
    -0.71
    +#+
    -0.71
    ături
    -0.70
    ()")
    -0.70
    POSITIVE LOGITS
     filles
    0.91
     girls
    0.75
     Mädchen
    0.70
     Oda
    0.68
    Girls
    0.65
    girls
    0.63
     daughters
    0.63
     Girls
    0.63
     fille
    0.59
    <h3>
    0.59
    Activations Density 0.138%

    No Known Activations