© 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 EvalsExportsinterp-engineNEWAPI 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. 197
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and processes

    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
     einerseits
    -0.69
     either
    -0.64
    either
    -0.63
     nämlich
    -0.63
     entweder
    -0.57
     namelijk
    -0.56
    Either
    -0.54
     ابتدا
    -0.54
     Either
    -0.53
     både
    -0.52
    POSITIVE LOGITS
     consequently
    1.10
     subsequently
    1.02
     consequent
    1.00
     consiguiente
    0.98
     importantly
    0.97
     subsequent
    0.94
    sequently
    0.92
     therefore
    0.91
     correspondingly
    0.88
    何より
    0.87
    Activations Density 1.195%

    No Known Activations