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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3753
    Prev
    Next
    INDEX
    Explanations

    references to nudity and related themes

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

    Nudity and related activities

    np_acts-logits-general · gemini-2.0-flash

    naked and nude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.52
    AndEndTag
    -0.45
    ruptedException
    -0.44
    🇶
    -0.44
    FXML
    -0.44
    yntaxException
    -0.43
     برانيه
    -0.43
     GenerationType
    -0.42
     pizarra
    -0.41
    الحياه
    -0.41
    POSITIVE LOGITS
     naked
    1.36
     Naked
    1.30
    Naked
    1.29
    naked
    1.24
     nude
    1.03
     nudity
    1.02
     bare
    1.00
    裸
    0.95
     desn
    0.94
     Bare
    0.91
    Activations Density 0.308%

    No Known Activations