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. 6322
    Prev
    Next
    INDEX
    Explanations

    terms related to metrics and indicators of energy or resource use

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

    ending in "-ity" or "-ty"

    np_acts-logits-general · gemini-2.0-flash

    words ending in ity or tory

    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
    est
    -0.78
    ings
    -0.76
    ם
    -0.65
    __(/*!
    -0.62
    an
    -0.61
    us
    -0.61
    ations
    -0.60
    ら
    -0.59
    ⇑
    -0.59
    в
    -0.58
    POSITIVE LOGITS
    tory
    1.13
    yyyy
    0.99
    yyy
    0.94
    antasy
    0.93
    PHONY
    0.92
    ARY
    0.89
     ary
    0.87
    arty
    0.86
    yyyyy
    0.85
     tary
    0.84
    Activations Density 1.207%

    No Known Activations