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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 2035
    Prev
    Next
    INDEX
    Explanations

    references to nudity and sexual actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.76
    DockStyle
    -0.72
    +:+
    -0.71
    KURZBESCHREIBUNG
    -0.69
    twimg
    -0.69
    ScopeManager
    -0.65
    setVerticalGroup
    -0.64
     Roskov
    -0.64
    homonymie
    -0.63
    oznam
    -0.62
    POSITIVE LOGITS
     naked
    1.63
     nude
    1.40
    naked
    1.40
     nudity
    1.37
     Naked
    1.33
     bare
    1.22
    Naked
    1.22
     exposing
    1.19
     desn
    1.18
    裸
    1.14
    Activations Density 0.150%

    No Known Activations