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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 1431
    Prev
    Next
    INDEX
    Explanations

    programming constructs and commands related to data handling and control flow

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

    Code snippets with increment/decrement operators

    np_acts-logits-general · gemini-2.0-flash

    incrementing code sequences

    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
     }{@
    -0.75
    +#+#
    -0.71
    WireFormatLite
    -0.69
    RTEE
    -0.67
     незавершена
    -0.67
    Portail
    -0.67
    SBATCH
    -0.62
     FetchType
    -0.61
    amaño
    -0.60
     parseFrom
    -0.59
    POSITIVE LOGITS
    ++);
    0.64
    ImageContext
    0.58
    ++]
    0.55
     disambiguazione
    0.51
    ++
    0.50
    ++];
    0.50
    发表于
    0.48
    ++]=
    0.48
    tuur
    0.48
    ++,
    0.47
    Activations Density 0.167%

    No Known Activations