© 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. 11-GEMMASCOPE-RES-16K
    11. 5246
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating necessity or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     étrangère
    -0.45
     citoy
    -0.43
     frío
    -0.40
     froide
    -0.39
     démocratique
    -0.39
     romantique
    -0.38
     hielo
    -0.38
    rašymas
    -0.38
     chaude
    -0.38
     judiciaire
    -0.36
    POSITIVE LOGITS
    SequentialGroup
    0.66
    transQ
    0.65
    ContentAlignment
    0.65
    ChildScrollView
    0.61
     canst
    0.60
    ValueStyle
    0.60
    parsedMessage
    0.60
    webElementGuid
    0.59
    KommentareTeilen
    0.57
    principalColumn
    0.56
    Activations Density 0.249%

    No Known Activations