© 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. 31-GEMMASCOPE-RES-16K
    11. 5539
    Prev
    Next
    INDEX
    Explanations

    expressions of concern or caution regarding health-related advice and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases expressing strong opinions or definitively making a point, especially using phrases like "there's no doubt" or "no denying".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    emphatic statements asserting certainty or negating doubt (phrases like "there is no denying," "no question," "won't hesitate," "don't delay").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    しか
    -0.37
     fijar
    -0.36
    धिक
    -0.34
    ?
    -0.32
     even
    -0.31
     only
    -0.31
     едва
    -0.29
    ография
    -0.29
      
    -0.29
     normally
    -0.28
    POSITIVE LOGITS
    Personensuche
    0.89
    SequentialGroup
    0.87
    VersionUID
    0.80
    WaitGroup
    0.75
    DockStyle
    0.70
     JpaRepository
    0.69
     transférez
    0.69
    Nor
    0.69
     Nor
    0.65
     sondern
    0.65
    Activations Density 0.304%

    No Known Activations