© 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. 34-GEMMASCOPE-RES-16K
    11. 10536
    Prev
    Next
    INDEX
    Explanations

    inquiries and statements reflecting personal opinions or decisions

    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
    GOTREF
    -0.65
    adaptiveStyles
    -0.64
    verwijspagina
    -0.54
     nahilalakip
    -0.54
     TextAppearance
    -0.53
    Aktualisiert
    -0.52
    Попис
    -0.51
    WithIOException
    -0.50
     ujednoznacz
    -0.50
    posedge
    -0.50
    POSITIVE LOGITS
     is
    2.77
     are
    1.47
     was
    1.43
     adalah
    1.33
     has
    1.27
     является
    1.25
     είναι
    1.21
     isn
    1.18
     belongs
    1.17
     ialah
    1.15
    Activations Density 8.487%

    No Known Activations