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. 25-GEMMASCOPE-RES-16K
    6. 7818
    Prev
    Next
    INDEX
    Explanations

    numerical data or values related to coordinates or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.71
     defaultstate
    -0.67
    ="@+
    -0.63
     EconPapers
    -0.63
    )|^{
    -0.57
    RetentionPolicy
    -0.56
    Tembelea
    -0.56
     indisponible
    -0.56
     Himo
    -0.56
     विश्वसनीयता
    -0.55
    POSITIVE LOGITS
      
    0.51
     Zum
    0.49
    ❷
    0.47
    piram
    0.47
    phazard
    0.45
    Await
    0.45
    ularity
    0.44
     FontFamily
    0.42
    haal
    0.42
     scal
    0.41
    Activations Density 0.112%

    No Known Activations