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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4239
    Prev
    Next
    INDEX
    Explanations

    references to legal arguments and assertions in a judicial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.59
    ngrx
    -0.54
     aastal
    -0.49
     AssemblyTitle
    -0.49
    podar
    -0.46
    ArgsConstructor
    -0.45
    addCriterion
    -0.45
     FetchType
    -0.44
    anyway
    -0.44
     stenosis
    -0.44
    POSITIVE LOGITS
     Administrativna
    0.70
     also
    0.67
     חיצוניים
    0.64
     kaarangay
    0.63
    Jereo
    0.63
    /**
    0.62
     pageContext
    0.61
    XmlAttribute
    0.60
     ModelExpression
    0.60
     dabei
    0.59
    Activations Density 1.021%

    No Known Activations