© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3-GEMMASCOPE-RES-16K
    11. 8440
    Prev
    Next
    INDEX
    Explanations

    mentions of specific places and historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     szé
    -0.39
     malheur
    -0.39
     comunicarse
    -0.38
     صوتيه
    -0.37
     vilá
    -0.36
     الرخصة
    -0.36
     kill
    -0.35
     onBind
    -0.35
     behövs
    -0.35
    nalités
    -0.34
    POSITIVE LOGITS
    Personendaten
    0.68
    wiki
    0.53
     bark
    0.52
    execSQL
    0.52
     dash
    0.50
     Servant
    0.50
    dash
    0.49
    servant
    0.49
     dashes
    0.46
    complexType
    0.46
    Activations Density 1.497%

    No Known Activations