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. 19-GEMMASCOPE-RES-16K
    6. 12
    Prev
    Next
    INDEX
    Explanations

    terms related to wrongful death legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.80
     виправивши
    -0.63
    styleType
    -0.60
    SourceChecksum
    -0.59
     OFDb
    -0.57
    ására
    -0.56
    SharedDtor
    -0.56
    étit
    -0.53
    ftagPool
    -0.53
    httphttps
    -0.52
    POSITIVE LOGITS
    Jeografia
    0.69
     victim
    0.66
     injury
    0.66
     injuries
    0.63
     claim
    0.62
     victims
    0.61
     Injury
    0.60
     Injuries
    0.59
     injured
    0.59
     Claim
    0.58
    Activations Density 0.272%

    No Known Activations