© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 12232
    Prev
    Next
    INDEX
    Explanations

    instances of text formatting or emphasis, particularly bold and strong tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.73
    IsContent
    -0.63
     <=",
    -0.62
    thâu
    -0.61
    AndEndTag
    -0.61
     betweenstory
    -0.60
     jspb
    -0.58
    IntoConstraints
    -0.58
     MainAxisSize
    -0.56
    arakhand
    -0.56
    POSITIVE LOGITS
    <u>
    1.07
    <em>
    0.96
    <strong>
    0.83
    </strong>
    0.81
    <i>
    0.75
    “
    0.70
    <b>
    0.69
    <s>
    0.66
    ‘
    0.65
    </u>
    0.62
    Activations Density 0.091%

    No Known Activations