© 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. 7061
    Prev
    Next
    INDEX
    Explanations

    negative expressions or terms implying doubt and uncertainty

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

    contractions and informal speech patterns (particularly "I'm", "it's", "that's", and "I've").

    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
    DrawerToggle
    -0.55
    IBOutlet
    -0.50
    migrationBuilder
    -0.48
    )‏
    -0.47
     clichés
    -0.46
    ということ
    -0.46
     آن‌ها
    -0.45
     fiancé
    -0.45
    ScopeManager
    -0.45
     fiancée
    -0.45
    POSITIVE LOGITS
     doesnt
    1.10
     wasnt
    1.05
     isnt
    1.05
    Dont
    1.03
     didnt
    1.01
     arent
    1.01
     Thats
    1.01
     Dont
    1.01
     Theres
    1.00
    Thats
    0.99
    Activations Density 0.281%

    No Known Activations