© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7468
    Prev
    Next
    INDEX
    Explanations

    legal concepts and arguments related to trial proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ه‌ی
    -0.42
    (…)
    -0.40
    

    -0.38
    (“
    -0.37
    🇶
    -0.37
     topik
    -0.37
     Raja
    -0.36
     videos
    -0.36
    gang
    -0.36
    oiden
    -0.36
    POSITIVE LOGITS
     "*
    0.65
     *
    0.60
     "`
    0.58
    featureID
    0.57
     '*
    0.51
     `"
    0.51
     `.
    0.50
     `
    0.47
    脚注の使い方
    0.47
    principalTable
    0.44
    Activations Density 5.172%

    No Known Activations