© 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. 34-GEMMASCOPE-RES-16K
    11. 11527
    Prev
    Next
    INDEX
    Explanations

    phrases related to requests for clarification or explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.52
    CppMethod
    -0.45
     GenerationType
    -0.45
     StatefulWidget
    -0.44
    hyrchwyd
    -0.44
     RemoteException
    -0.43
    bolista
    -0.42
    ضايا
    -0.41
    nestjs
    -0.40
     tém
    -0.40
    POSITIVE LOGITS
     explanation
    3.28
     explain
    3.14
     explanations
    3.05
     explaining
    2.94
     explained
    2.91
     Explanation
    2.73
     explains
    2.72
    explain
    2.69
    explanation
    2.66
     explica
    2.59
    Activations Density 0.957%

    No Known Activations