© 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. 11670
    Prev
    Next
    INDEX
    Explanations

    elements related to revealing secrets or exposing hidden information

    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
     الحره
    -0.60
     kasarigan
    -0.56
    principalColumn
    -0.48
     Zeichen
    -0.43
    oa̍t
    -0.42
    complexContent
    -0.41
    ragamo
    -0.41
    yticks
    -0.39
     Ansprechpartner
    -0.39
    Parameteri
    -0.38
    POSITIVE LOGITS
     reveal
    2.69
     revealed
    2.58
     revealing
    2.53
     revelation
    2.34
     Reveal
    2.33
     reveals
    2.33
    reveal
    2.33
     revelations
    2.25
     disclosure
    2.22
    revealed
    2.22
    Activations Density 0.891%

    No Known Activations