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. 16-GEMMASCOPE-RES-16K
    6. 16096
    Prev
    Next
    INDEX
    Explanations

    formal references to locations and events

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

    Text following "The," "About," "For," or "Here"

    np_acts-logits-general · gemini-2.0-flash

    ABOUT, Surf, Bars, Mc, Life, SKU

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -1.29
    IsMutable
    -1.27
    UserScript
    -1.25
    abestanden
    -1.22
    تقاوى
    -1.21
     Савезне
    -1.21
     ་་
    -1.17
     Meksiku
    -1.14
    脚注の使い方
    -1.12
     itſelf
    -1.11
    POSITIVE LOGITS
    <eos>
    1.27
     
    0.94
    ↵↵
    0.94
    ↵
    0.91
     I
    0.84
    I
    0.81
    1
    0.81
    The
    0.80
    :
    0.78
     The
    0.73
    Activations Density 1.351%

    No Known Activations