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. 5-GEMMASCOPE-RES-16K
    6. 11013
    Prev
    Next
    INDEX
    Explanations

    words indicating estimation or approximation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -0.50
    anello
    -0.50
     II
    -0.50
     I
    -0.49
    D
    -0.48
    L
    -0.48
    Yii
    -0.47
    вая
    -0.46
     most
    -0.46
    II
    -0.45
    POSITIVE LOGITS
     approximately
    1.93
    approximately
    1.88
     Approximately
    1.77
     approx
    1.75
     Approx
    1.75
    Approximately
    1.74
     approxim
    1.73
    approx
    1.67
     approximate
    1.62
    Approx
    1.60
    Activations Density 0.185%

    No Known Activations