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. 16-GEMMASCOPE-RES-16K
    6. 14865
    Prev
    Next
    INDEX
    Explanations

    words related to accidents and injuries

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

    Reports of accidents and injuries

    np_acts-logits-general · gemini-2.0-flash

    physical injury and 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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.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
     tartalomajánló
    -0.68
    contentLoaded
    -0.67
    KommentareTeilen
    -0.64
    exitRule
    -0.59
    DeleteBehavior
    -0.59
    Hochspringen
    -0.58
     defStyle
    -0.56
    AndEndTag
    -0.56
    fjspx
    -0.55
    +#+#
    -0.55
    POSITIVE LOGITS
     damage
    0.72
     injuries
    0.72
     injury
    0.71
     injured
    0.66
     injure
    0.63
     wounds
    0.62
     hurt
    0.59
     Injuries
    0.59
     Injury
    0.59
     Injured
    0.59
    Activations Density 0.243%

    No Known Activations