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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 12797
    Prev
    Next
    INDEX
    Explanations

    numeric values and symbols, likely indicating code or structured data elements

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

    Code, database, and file-related terms

    np_acts-logits-general · gemini-2.0-flash

    code snippets

    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
    fjspx
    -0.59
    WithIOException
    -0.58
     Celui
    -0.55
     works
    -0.55
     cherchés
    -0.54
    iones
    -0.54
    mybatisplus
    -0.54
     EconPapers
    -0.53
    WriteBarrier
    -0.53
     SwiftUI
    -0.53
    POSITIVE LOGITS
            
    0.57
    Personensuche
    0.55
    IntoConstraints
    0.54
     дописавши
    0.49
     Privacidade
    0.47
    sidemargin
    0.45
     parcela
    0.45
     lenker
    0.45
    EndGlobal
    0.44
    TargetException
    0.44
    Activations Density 0.041%

    No Known Activations