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. 12876
    Prev
    Next
    INDEX
    Explanations

    technical terms and variables related to mathematical and scientific formulations

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

    Mathematical or chemical formulas

    np_acts-logits-general · gemini-2.0-flash

    type with

    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
     مشين
    -0.51
    bcryptjs
    -0.49
    aarrggbb
    -0.48
    AndEndTag
    -0.47
    Dearest
    -0.46
    umumkan
    -0.46
     pertence
    -0.45
    обеди
    -0.45
     éti
    -0.44
     combineReducers
    -0.44
    POSITIVE LOGITS
     незавершена
    0.76
     HttpNotFound
    0.65
    WebElementEntity
    0.64
    SBATCH
    0.64
    发表于
    0.61
     Vikipedi
    0.59
     externi
    0.58
    مصادر
    0.57
    Abp
    0.56
     المعيارى
    0.55
    Activations Density 2.677%

    No Known Activations