© 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. 7737
    Prev
    Next
    INDEX
    Explanations

    technical jargon and terminologies related to systems 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
     EconPapers
    -0.57
    oa̍t
    -0.52
    +#+
    -0.47
    یرات
    -0.46
     kasarigan
    -0.45
    (&:
    -0.42
    delwed
    -0.41
    polazione
    -0.39
    újo
    -0.38
    gnore
    -0.36
    POSITIVE LOGITS
     some
    3.56
    some
    2.95
     некоторые
    2.80
     algunos
    2.80
    Some
    2.78
     Some
    2.77
     некоторых
    2.72
     alguns
    2.66
     alcuni
    2.61
     algunas
    2.59
    Activations Density 3.725%

    No Known Activations