© 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. 39-GEMMASCOPE-RES-16K
    11. 4284
    Prev
    Next
    INDEX
    Explanations

    references to decisions, judgment, and relationships in legal and interpersonal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.51
    IUrlHelper
    -0.49
    May
    -0.48
     Roskov
    -0.46
    可
    -0.45
    ConstraintMaker
    -0.42
    endwhile
    -0.41
     May
    -0.41
     cappuccio
    -0.38
    puede
    -0.38
    POSITIVE LOGITS
     might
    2.72
    Might
    2.27
    might
    2.20
     Might
    2.13
     MIGHT
    1.47
     migh
    0.94
     mighty
    0.86
     mig
    0.86
     Mighty
    0.75
     pourraient
    0.75
    Activations Density 0.454%

    No Known Activations