© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 622
    Prev
    Next
    INDEX
    Explanations

    references to explicit sexual actions and anatomical interactions

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

    sexual acts and related anatomical references

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

    inside or within

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    IndentedString
    -0.77
     otomatig
    -0.71
    Lähteet
    -0.65
     purpoſe
    -0.65
    DebuggerNonUser
    -0.64
    ChildIndex
    -0.64
    ſelf
    -0.62
     houſe
    -0.61
     pleaſure
    -0.61
    msgTypes
    -0.61
    POSITIVE LOGITS
     inside
    1.14
     underneath
    0.98
    inside
    0.97
     beneath
    0.92
     between
    0.90
     under
    0.90
     INSIDE
    0.90
    Inside
    0.90
     behind
    0.85
     Inside
    0.84
    Activations Density 0.125%

    No Known Activations