© 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. 7-GEMMASCOPE-RES-16K
    6. 1311
    Prev
    Next
    INDEX
    Explanations

    terms related to peaks and pressure in data distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kot
    -0.78
     Kot
    -0.74
    .........
    -0.71
     Butterfield
    -0.69
    </strong>
    -0.66
    MathML
    -0.64
    Stuff
    -0.64
     fact
    -0.61
    perso
    -0.60
    いる
    -0.59
    POSITIVE LOGITS
     peaks
    1.68
     PEAK
    1.66
     Peak
    1.66
     peak
    1.62
     Peaks
    1.58
    Peak
    1.55
    peak
    1.41
    peaks
    1.35
     peaking
    1.23
     peaked
    1.22
    Activations Density 0.091%

    No Known Activations