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. 2233
    Prev
    Next
    INDEX
    Explanations

    numeric data, especially related to codes and performance metrics

    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
    GEBURTSDATUM
    -0.82
    PositiveButton
    -0.74
    minipage
    -0.71
     Trey
    -0.70
    RetentionPolicy
    -0.68
    httphttps
    -0.67
    Παραπομπές
    -0.66
    InjectAttribute
    -0.64
     оригіналу
    -0.62
     Tula
    -0.62
    POSITIVE LOGITS
     onCreateView
    0.57
    publique
    0.57
    kespea
    0.55
    signals
    0.55
    FORMAN
    0.51
     CLAIMS
    0.50
     claims
    0.50
    arResult
    0.50
     CURIAM
    0.50
    gör
    0.50
    Activations Density 0.232%

    No Known Activations