© 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. 35-GEMMASCOPE-RES-16K
    11. 10881
    Prev
    Next
    INDEX
    Explanations

    references to potential risks or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.63
    postsleuth
    -0.62
     provavelmente
    -0.62
     posiblemente
    -0.59
     probabilmente
    -0.57
     probablemente
    -0.57
     autorytatywna
    -0.56
     يتيمه
    -0.55
     waarschijnlijk
    -0.55
     resourceCulture
    -0.52
    POSITIVE LOGITS
     future
    0.65
     candidates
    0.64
     pitfalls
    0.61
    %)$
    0.56
     dangers
    0.52
     candidate
    0.52
    y
    0.51
     sources
    0.49
    future
    0.48
     suitors
    0.48
    Activations Density 0.238%

    No Known Activations