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 - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 4669
    Prev
    Next
    INDEX
    Explanations

    mentions of vehicle-related components and their issues, particularly concerning safety and operational state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.68
     мәкал
    -0.66
    Autoritní
    -0.66
    berdayakan
    -0.65
     GenerationType
    -0.64
    قایناق‌لار
    -0.64
     Majefty
    -0.61
     quelcon
    -0.60
    دانشنامهٔ
    -0.59
     giustizia
    -0.58
    POSITIVE LOGITS
     adequately
    0.70
     sufficiently
    0.61
     safe
    0.60
     safely
    0.58
     neutral
    0.58
     calm
    0.57
     protected
    0.56
    ()));
    
    0.55
     stable
    0.55
     adequate
    0.55
    Activations Density 0.728%

    No Known Activations