© 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 EvalsExportsinterp-engineNEWAPI 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. 9347
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in textual data

    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
    “
    -0.76
    "
    -0.56
    ...
    -0.52
    -
    -0.46
    …
    -0.44
    —
    -0.42
    ?
    -0.41
    .
    -0.40
    !
    -0.39
    accompag
    -0.37
    POSITIVE LOGITS
    ValueStyle
    1.05
     propOrder
    0.97
     ...)
    0.92
     autorytatywna
    0.91
     kasarigan
    0.88
     >=",
    0.87
    存于互联网档案馆
    0.86
     Infórmanos
    0.85
     …)
    0.84
     resourceCulture
    0.82
    Activations Density 0.505%

    No Known Activations