© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 755
    Prev
    Next
    INDEX
    Explanations

    terms related to sexuality and sexual conduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ✨:
    -0.49
     Vikipedi
    -0.49
     testicular
    -0.45
    invokeLater
    -0.44
    InitVars
    -0.41
     Ridge
    -0.40
    corporation
    -0.40
    inSlope
    -0.39
     Deadline
    -0.39
     Lined
    -0.39
    POSITIVE LOGITS
    panou
    0.48
    aarrggbb
    0.45
    PONENT
    0.43
    CrossRef
    0.42
    sidemargin
    0.42
    новништво
    0.41
    ually
    0.41
    stdint
    0.41
    AndEndTag
    0.40
     órgano
    0.38
    Activations Density 0.149%

    No Known Activations