© 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. 7-GEMMASCOPE-RES-16K
    11. 10914
    Prev
    Next
    INDEX
    Explanations

    the presence of dashes or special characters used for formatting or sectioning text

    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
     „
    -0.94
    ات
    -0.78
     Wey
    -0.72
    '],
    -0.71
     Edel
    -0.71
    mappedBy
    -0.69
    "],
    -0.68
    „
    -0.68
    gewiesen
    -0.67
    ָל
    -0.67
    POSITIVE LOGITS
    .--
    1.58
    --
    1.56
    ,--
    1.55
    "--
    1.55
    //--
    1.52
    !--
    1.49
    '--
    1.47
    --"
    1.39
    #--
    1.38
     --
    1.34
    Activations Density 0.214%

    No Known Activations