© 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. 38-GEMMASCOPE-RES-16K
    11. 12406
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and references within scientific or technical texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kiin
    -0.35
     abbraccio
    -0.30
     tunn
    -0.30
     hiér
    -0.29
    ようになります
    -0.29
     princí
    -0.28
     friv
    -0.28
     salaire
    -0.27
     royaume
    -0.27
     âge
    -0.27
    POSITIVE LOGITS
     autorytatywna
    1.02
     صوتيه
    0.85
     المعيارى
    0.82
     '\\;'
    0.79
    ########.
    0.70
     يتيمه
    0.70
    <unused51>
    0.68
    <unused14>
    0.68
    <unused7>
    0.68
    [@BOS@]
    0.68
    Activations Density 0.323%

    No Known Activations