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. 18-GEMMASCOPE-RES-16K
    6. 590
    Prev
    Next
    INDEX
    Explanations

    mentions or references, particularly in the context of citations or notable acknowledgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentioning or citing

    np_acts-logits-general · gemini-2.0-flash

    citing or mentioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interpreted
    -0.55
     détermination
    -0.54
    DataAnnotations
    -0.53
     وتسجيلات
    -0.51
     giản
    -0.51
     beſt
    -0.51
    réhen
    -0.50
     ſy
    -0.50
    viewDidLoad
    -0.48
     handleMessage
    -0.48
    POSITIVE LOGITS
     mention
    2.21
     Mention
    1.87
     mentions
    1.80
    mention
    1.74
     mentioning
    1.70
    Mention
    1.68
     mentioned
    1.64
     mencionar
    1.48
     mencion
    1.44
     Mentioned
    1.44
    Activations Density 0.389%

    No Known Activations