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. 22-GEMMASCOPE-RES-16K
    6. 13966
    Prev
    Next
    INDEX
    Explanations

    programming-related function calls and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OfBirth
    -0.83
    ly
    -0.68
    Error
    -0.64
    Subject
    -0.61
    Nro
    -0.59
    FirstName
    -0.57
    Options
    -0.55
    Selection
    -0.55
    Bounds
    -0.53
    to
    -0.53
    POSITIVE LOGITS
     defaultstate
    0.63
     SwiftUI
    0.59
    HtmlAttribute
    0.59
    :+:
    0.58
    GraphicsUnit
    0.57
    newtheorem
    0.56
    ]));
    
    0.55
    tadır
    0.55
     valt
    0.55
    reactstrap
    0.54
    Activations Density 0.102%

    No Known Activations