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. 3647
    Prev
    Next
    INDEX
    Explanations

    the use of the syllable "sp."

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

    Token "sp" followed by another token

    np_acts-logits-general · gemini-2.0-flash

    words starting with sp

    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
     overseas
    -0.45
    mery
    -0.44
    клопе
    -0.43
     Galería
    -0.43
     dead
    -0.42
     PropTypes
    -0.42
     جمع
    -0.42
    IEU
    -0.40
    Mell
    -0.40
    гови
    -0.39
    POSITIVE LOGITS
    帖最后由
    0.93
     nakalista
    0.76
    ngdoc
    0.75
    RenderAtEndOf
    0.72
     فريبيس
    0.69
     مشين
    0.68
    IsMutable
    0.68
    ConstraintMaker
    0.67
    vician
    0.67
     StatefulWidget
    0.65
    Activations Density 0.114%

    No Known Activations