© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 6015
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to criminal accountability and sentencing guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the Guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Speise
    -0.37
     whistles
    -0.35
     AssemblyTitle
    -0.35
     summaries
    -0.35
    kog
    -0.35
    rillation
    -0.34
     Cultures
    -0.33
    Reprodução
    -0.33
    makeConstraints
    -0.33
    zny
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.58
    mobileqq
    0.56
    Skocz
    0.56
     betweenstory
    0.53
    PyExc
    0.52
    BitConverter
    0.51
     Guidelines
    0.50
    
    0.50
    Guidelines
    0.49
    :✨
    0.48
    Activations Density 0.503%

    No Known Activations