© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 3743
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and variables commonly used in equations or formulas

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

    Mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.63
     both
    -0.52
     her
    -0.52
    </i>
    -0.47
    ارت
    -0.46
    次
    -0.46
     his
    -0.46
     a
    -0.44
     much
    -0.43
     su
    -0.43
    POSITIVE LOGITS
    Portály
    0.90
    InjectAttribute
    0.89
     negroes
    0.82
     Мексичка
    0.79
    UnsafeEnabled
    0.79
     تانيه
    0.78
     Autorisations
    0.75
     wikipagina
    0.74
     للمعارف
    0.74
    SourceChecksum
    0.73
    Activations Density 0.671%

    No Known Activations