© 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. 33-GEMMASCOPE-RES-16K
    11. 1287
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss the significance or function of various roles in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ように
    -0.43
    -------------</
    -0.38
    rostis
    -0.38
    denominator
    -0.36
     Neum
    -0.36
    rollable
    -0.35
    UnifiedTopology
    -0.35
    ்
    -0.35
    redirect
    -0.34
     Loft
    -0.34
    POSITIVE LOGITS
     getRole
    0.96
     autorytatywna
    0.84
     Role
    0.75
     role
    0.72
     roleId
    0.72
     ROLE
    0.71
    Role
    0.71
    played
    0.69
     played
    0.66
    扮演
    0.65
    Activations Density 0.088%

    No Known Activations