Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 14533
    Prev
    Next
    INDEX
    Explanations

    discussions around personal experiences with relationships and intimacy

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

    Following certain adverbs of frequency

    np_acts-logits-general · gemini-2.0-flash

    happens often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.74
    первых
    -0.73
    featureID
    -0.69
     nakalista
    -0.61
     successive
    -0.60
    tagHelperRunner
    -0.59
    BagConstraints
    -0.56
     frattempo
    -0.56
    ionario
    -0.56
    __':
    
    -0.56
    POSITIVE LOGITS
     frequently
    1.24
     alot
    1.18
     regularly
    1.12
    frequently
    1.06
     frequ
    1.04
     paljon
    1.02
     Frequently
    1.00
     frequency
    0.98
     lots
    0.98
     more
    0.97
    Activations Density 0.283%

    No Known Activations