© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 16162
    Prev
    Next
    INDEX
    Explanations

    specific explicit sexual activities and related terms

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

    Text near percentages, deletions, or sex

    np_acts-logits-general · gemini-2.0-flash

    responsible for

    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
    ">//
    -0.66
    openzeppelin
    -0.55
    AutoScaleMode
    -0.54
    //
    -0.53
    ">—
    -0.53
     Sando
    -0.53
     Roskov
    -0.51
    嶼
    -0.50
    alva
    -0.48
     Bellow
    -0.47
    POSITIVE LOGITS
     surla
    0.64
    ImageContext
    0.63
    ScopeManager
    0.56
    gypti
    0.52
    obenzene
    0.52
    الحياه
    0.51
    édrale
    0.51
     aikaa
    0.50
    ernalia
    0.49
    })}$
    0.49
    Activations Density 0.038%

    No Known Activations