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. 14-GEMMASCOPE-RES-16K
    6. 12712
    Prev
    Next
    INDEX
    Explanations

    specialized scientific and technical terms or jargon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.87
     الحره
    -0.83
    AndEndTag
    -0.82
     betweenstory
    -0.81
     <<<<<<<<<<<<<<
    -0.78
    ackerel
    -0.78
    RegressionTest
    -0.74
    verwijspagina
    -0.73
     Baillargeon
    -0.70
     للاسماء
    -0.69
    POSITIVE LOGITS
    Longest
    0.42
    Fixed
    0.41
    EndOf
    0.41
    niko
    0.41
    まま
    0.39
    สิน
    0.38
    aab
    0.38
     Longest
    0.38
    UrlResolution
    0.37
    amerikanischer
    0.37
    Activations Density 0.782%

    No Known Activations