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. 10986
    Prev
    Next
    INDEX
    Explanations

    phrases related to making the most of a situation or maximizing outcomes

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

    [Word] out of [something]

    np_acts-logits-general · gemini-2.0-flash

    make the most out of

    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
     OnTriggerEnter
    -0.63
    UnusedPrivate
    -0.59
     muualla
    -0.58
    Tembelea
    -0.54
    AnimationsModule
    -0.51
     SwiftUI
    -0.50
    bouncycastle
    -0.50
     UIImageView
    -0.50
     CURLOPT
    -0.48
     createSlice
    -0.48
    POSITIVE LOGITS
     out
    1.45
     outta
    1.16
     Out
    1.02
    Out
    0.93
    out
    0.89
    出
    0.89
     daraus
    0.88
     OUT
    0.84
    出了
    0.76
     extracting
    0.75
    Activations Density 0.177%

    No Known Activations