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. 20-GEMMASCOPE-RES-16K
    6. 6601
    Prev
    Next
    INDEX
    Explanations

    references to physical attributes and sexually suggestive imagery

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

    relating to buttocks and genitals

    np_acts-logits-general · gemini-2.0-flash

    body parts and genitalia

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.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
    awtextra
    -0.69
    دانشنامهٔ
    -0.66
    principalTable
    -0.65
    oredCriteria
    -0.64
     defaultstate
    -0.63
    preventDefault
    -0.60
    ')['
    -0.58
    adaptiveStyles
    -0.56
    expandindo
    -0.56
    KURZBESCHREIBUNG
    -0.55
    POSITIVE LOGITS
     ass
    1.41
     butt
    1.39
     buttocks
    1.29
     arse
    1.21
     butts
    1.14
    butt
    1.08
     asses
    1.06
     Butt
    1.03
     ASS
    0.93
     backside
    0.92
    Activations Density 0.243%

    No Known Activations