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. 6642
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical phenomena and electrostatics

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

    before suffixes like "statics", "therapy", or "otide"

    np_acts-logits-general · gemini-2.0-flash

    electrical phenomena

    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
    complexContent
    -0.71
    er
    -0.69
    indest
    -0.68
    ling
    -0.61
    ar
    -0.58
    ly
    -0.58
    ter
    -0.58
     fotografico
    -0.57
    SerializedSize
    -0.57
    л
    -0.56
    POSITIVE LOGITS
    ので
    0.77
     Hough
    0.74
     Crusoe
    0.70
    mybatisplus
    0.70
    isticated
    0.66
    adaptiveStyles
    0.65
     ||=
    0.63
    Rhestr
    0.62
    dientemente
    0.62
    nione
    0.62
    Activations Density 0.651%

    No Known Activations