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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11503
    Prev
    Next
    INDEX
    Explanations

    references to compensatory damages in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     velho
    -0.33
    Carriera
    -0.31
     ch
    -0.31
    darah
    -0.29
     normais
    -0.29
     familières
    -0.28
    渣
    -0.27
     volontaire
    -0.27
     jeito
    -0.27
    DLL
    -0.27
    POSITIVE LOGITS
     damages
    0.86
     Damages
    0.82
    Dama
    0.64
     damage
    0.62
     nakalista
    0.60
     Administrativna
    0.60
    Datuak
    0.59
     injured
    0.58
     injuries
    0.58
    RegressionTest
    0.58
    Activations Density 0.694%

    No Known Activations