© 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. 10-GEMMASCOPE-RES-16K
    11. 3344
    Prev
    Next
    INDEX
    Explanations

    programming concepts and terms related to user interface elements and component interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁢
    -0.52
     initComponents
    -0.39
     aren
    -0.38
    Personendaten
    -0.36
    SuppressMessage
    -0.36
     uits
    -0.35
     comigo
    -0.35
     young
    -0.34
     تضيفلها
    -0.34
     enfri
    -0.34
    POSITIVE LOGITS
    EReference
    0.60
    ௃
    0.52
    <unused43>
    0.52
    <unused42>
    0.52
     ſelb
    0.51
    <unused76>
    0.51
    <unused41>
    0.51
    <unused20>
    0.51
    [@BOS@]
    0.51
    <pad>
    0.51
    Activations Density 1.205%

    No Known Activations