© 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. 38-GEMMASCOPE-RES-16K
    11. 15270
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and judicial outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desmotivaciones
    -0.85
     Theſe
    -0.81
     Wikiseite
    -0.80
     rumahnya
    -0.78
     dalamnya
    -0.77
    berdayakan
    -0.76
     snippetHide
    -0.75
     conmigo
    -0.74
     Bewußt
    -0.74
     keduanya
    -0.72
    POSITIVE LOGITS
    <unused61>
    0.43
    <unused62>
    0.43
    <unused60>
    0.43
    ʺ
    0.39
    ↵
    0.38
    <unused63>
    0.37
    ​
    0.36
    IND
    0.35
    <0xE2>
    0.35
    TO
    0.35
    Activations Density 7.238%

    No Known Activations