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. 1-GEMMASCOPE-RES-16K
    6. 9303
    Prev
    Next
    INDEX
    Explanations

    terms related to computer systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imageNamed
    -0.73
     Audiodateien
    -0.69
     }}"></
    -0.64
    ագրություններ
    -0.62
    }],
    
    -0.61
    initializeApp
    -0.61
    </tfoot>
    -0.59
     argc
    -0.58
     useContext
    -0.57
    providedIn
    -0.57
    POSITIVE LOGITS
     systems
    0.98
    CompilerServices
    0.82
    systems
    0.77
     SYSTEMS
    0.70
     Systems
    0.67
     systèmes
    0.65
    ftagPool
    0.64
    Systems
    0.63
     formatting
    0.62
     rights
    0.62
    Activations Density 0.097%

    No Known Activations