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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10237
    Prev
    Next
    INDEX
    Explanations

    terms related to sexual and vocal characteristics

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

    ending in "al" or relating to viruses

    np_acts-logits-general · gemini-2.0-flash

    words ending in -al

    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
     Paglinawan
    -0.75
    tvguidetime
    -0.63
    //
    -0.63
    #
    -0.56
    tiglie
    -0.56
    reportWebVitals
    -0.55
    getvalue
    -0.55
    coroutines
    -0.54
    는
    -0.54
     manquer
    -0.54
    POSITIVE LOGITS
    ized
    1.94
    ization
    1.73
    izing
    1.57
    istic
    1.57
    isation
    1.53
    ists
    1.49
    ize
    1.45
    izes
    1.37
    ist
    1.34
    ism
    1.34
    Activations Density 0.722%

    No Known Activations