© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 6076
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or proper nouns that may indicate significant entities or subjects in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.72
     hObject
    -0.58
    DataAnnotations
    -0.58
     consultato
    -0.58
    rungsseite
    -0.58
     kasarigan
    -0.57
    AutoScaleMode
    -0.57
    TabLayout
    -0.56
    ῖς
    -0.56
    matchCondition
    -0.56
    POSITIVE LOGITS
     especially
    1.83
     particularly
    1.83
     Particularly
    1.67
    Especially
    1.65
    particularly
    1.62
    especially
    1.61
     Especially
    1.54
     particularmente
    1.50
     especialmente
    1.50
    尤其
    1.39
    Activations Density 0.481%

    No Known Activations