Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53538
    Prev
    Next
    INDEX
    Explanations

    references to accidents or injuries involving vehicles

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

    injury or damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.72
     tartalomajánló
    -0.70
     للاسماء
    -0.68
    rrggbb
    -0.62
     épu
    -0.58
    exitRule
    -0.57
    最快更新
    -0.56
    وردار
    -0.56
    fjspx
    -0.55
     Branche
    -0.55
    POSITIVE LOGITS
     injury
    0.69
     damage
    0.69
     injuries
    0.68
     injure
    0.60
     Injury
    0.60
     injured
    0.59
     Damage
    0.59
     Injuries
    0.57
    damage
    0.56
     injuring
    0.54
    Activations Density 0.246%

    No Known Activations