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. 24-GEMMASCOPE-RES-16K
    6. 4360
    Prev
    Next
    INDEX
    Explanations

    terms related to accidents and personal injury liability

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

    surrounding "accident" or "crash"

    np_acts-logits-general · gemini-2.0-flash

    accidents and injuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.69
     للمعارف
    -0.66
    ResumeLayout
    -0.64
     Roskov
    -0.61
    Gambas
    -0.61
    ècie
    -0.61
    TypedDataSet
    -0.60
     تانيه
    -0.59
    ôl
    -0.58
    IBOutlet
    -0.58
    POSITIVE LOGITS
     accidents
    1.58
     accident
    1.50
    accident
    1.24
     Accidents
    1.21
     accidente
    1.14
     injury
    1.14
     injuries
    1.12
     Accident
    1.10
    acc
    1.09
     accidentes
    1.08
    Activations Density 0.237%

    No Known Activations