© 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. 33-GEMMASCOPE-RES-16K
    11. 11607
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to legal proceedings and jury discussions

    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
    majánló
    -1.48
     beſch
    -1.37
    ſicht
    -1.35
     témoig
    -1.34
     verſch
    -1.34
     Weiſe
    -1.30
     ſeines
    -1.30
    <unused14>
    -1.28
    <unused3>
    -1.28
    <pad>
    -1.28
    POSITIVE LOGITS
     AND
    0.46
     L
    0.45
     UN
    0.43
     Y
    0.42
     NOT
    0.41
     R
    0.41
     NO
    0.39
     H
    0.39
     D
    0.39
     ST
    0.39
    Activations Density 1.624%

    No Known Activations