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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 456
    Prev
    Next
    INDEX
    Explanations

    references to the Apache Commons library and its components

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

    "apache"

    np_acts-logits-general · gemini-2.0-flash

    apache

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.71
    scryfall
    -0.65
    يكب
    -0.63
     ویکی‌پدی
    -0.62
     NSCoder
    -0.62
    ramienta
    -0.60
    SourceChecksum
    -0.60
    FilterChain
    -0.59
    verwijspagina
    -0.59
     Geraadpleegd
    -0.58
    POSITIVE LOGITS
    apache
    1.46
     Apache
    1.24
     apache
    1.23
    Apache
    1.03
     Inſ
    0.73
    ACHE
    0.73
    ſelf
    0.71
     Reſ
    0.67
     Majefty
    0.65
     Perſ
    0.64
    Activations Density 0.136%

    No Known Activations