© 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. 14228
    Prev
    Next
    INDEX
    Explanations

    statements attributed to individuals, particularly those expressing opinions or feelings

    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
    StructEnd
    -0.72
     MainAxisSize
    -0.69
     queſta
    -0.68
     ſche
    -0.59
    localctx
    -0.59
    tagext
    -0.58
    MLLoader
    -0.57
    featureID
    -0.57
    Brainz
    -0.57
    tangentMode
    -0.57
    POSITIVE LOGITS
     quote
    0.61
    quote
    0.59
    Quote
    0.55
     QUOTE
    0.48
     Quote
    0.46
    <i>
    0.45
    QUOTE
    0.44
    <em>
    0.42
     “…
    0.42
    <blockquote>
    0.41
    Activations Density 0.152%

    No Known Activations