© 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. 15335
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical engineering concepts

    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
     wasn
    -0.64
    redacted
    -0.62
    IntoConstraints
    -0.62
     متعلقه
    -0.60
     weren
    -0.59
    wasn
    -0.58
    handelt
    -0.55
     PREVIOUS
    -0.54
     LOOKING
    -0.54
     didn
    -0.53
    POSITIVE LOGITS
    setVerticalGroup
    0.82
    ⓧ
    0.69
    PMailer
    0.63
    UnsafeEnabled
    0.63
     Ause
    0.61
     gewöhnlich
    0.60
    gages
    0.60
     généraux
    0.58
     algemeen
    0.58
    Viki
    0.57
    Activations Density 1.148%

    No Known Activations