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. 22-GEMMASCOPE-RES-16K
    6. 11007
    Prev
    Next
    INDEX
    Explanations

    terms related to sexual activity and anatomical references

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

    Punctuation, conjunctions, and prepositions

    np_acts-logits-general · gemini-2.0-flash

    Romanian names and grammar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.67
     itſelf
    -1.65
     Anſ
    -1.62
     Reſ
    -1.61
     pleaſure
    -1.59
     Efq
    -1.55
     purpoſe
    -1.55
     Monfieur
    -1.55
     Diſ
    -1.54
     raiſ
    -1.52
    POSITIVE LOGITS
     la
    0.73
     de
    0.71
     
    0.64
     si
    0.64
     a
    0.63
     sa
    0.62
    ,
    0.61
     o
    0.59
     une
    0.58
     in
    0.57
    Activations Density 0.022%

    No Known Activations