© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1497
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to judicial processes and criteria

    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
    Jeografia
    -0.54
    agisse
    -0.51
    UserScript
    -0.51
     للمعارف
    -0.50
    テンツ
    -0.49
     دیکھیے
    -0.49
    rinology
    -0.48
    المكان
    -0.48
    UnknownFieldSet
    -0.46
     defaultstate
    -0.46
    POSITIVE LOGITS
     certain
    3.41
    certain
    2.95
    Certain
    2.88
     Certain
    2.86
     tertentu
    2.61
     particular
    2.53
     bestimmte
    2.48
     CERTAIN
    2.47
     bestimmten
    2.47
     bepaalde
    2.39
    Activations Density 1.733%

    No Known Activations