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. 2-GEMMASCOPE-RES-16K
    6. 3651
    Prev
    Next
    INDEX
    Explanations

    elements related to function calls and assertions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.77
    Aiheesta
    -0.63
     flamengo
    -0.61
    zkod
    -0.59
     Zorg
    -0.59
     Aene
    -0.58
     forgetting
    -0.58
    rairie
    -0.58
    Skocz
    -0.58
    silia
    -0.57
    POSITIVE LOGITS
     disambiguazione
    0.61
    كويكب
    0.53
    
    0.50
     Normdatei
    0.50
     @"/
    0.50
     beginnetje
    0.50
     lenker
    0.48
    "><!--
    0.46
     HttpNotFound
    0.46
    قایناق‌لار
    0.46
    Activations Density 0.191%

    No Known Activations