© 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. 35-GEMMASCOPE-RES-16K
    11. 13634
    Prev
    Next
    INDEX
    Explanations

    technical or legal distinctions and clarifications involving processes or classifications

    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
     EconPapers
    -0.46
    endphp
    -0.41
     TextAlign
    -0.39
    ьажоргаш
    -0.38
     الحره
    -0.37
     resourceCulture
    -0.35
    gameserver
    -0.35
     ffilmiau
    -0.35
    Cyfarwyddwr
    -0.34
    ыгана
    -0.34
    POSITIVE LOGITS
     distinguish
    2.75
     distinction
    2.69
     differentiate
    2.63
     distinguishing
    2.53
     differentiating
    2.52
     differentiation
    2.41
     distinctions
    2.41
     differentiates
    2.38
     distinguishes
    2.36
     distingu
    2.33
    Activations Density 1.296%

    No Known Activations