© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12529
    Prev
    Next
    INDEX
    Explanations

    rules and structures related to data analysis and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    testens
    -0.63
    Equivalent
    -0.60
    tableFuture
    -0.58
     onAnimation
    -0.57
     hadapan
    -0.55
    ionista
    -0.55
     fallu
    -0.55
    '}';
    -0.55
    elfth
    -0.55
    FXMLLoader
    -0.53
    POSITIVE LOGITS
    规律
    0.81
     patterns
    0.80
     pattern
    0.79
     disambiguazione
    0.72
     trend
    0.69
     Patterns
    0.68
    rungsseite
    0.63
    Pattern
    0.62
     rule
    0.62
    patterns
    0.61
    Activations Density 1.163%

    No Known Activations