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. 16118
    Prev
    Next
    INDEX
    Explanations

    constructs related to technical specifications and components, particularly in engineering or technological contexts

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

    preceding coordinating conjunctions or conjunctive adverbs

    np_acts-logits-general · gemini-2.0-flash

    starting punctuation and special characters

    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
    UnusedPrivate
    -0.89
     незавершена
    -0.89
     '\\;'
    -0.87
     صوتيه
    -0.86
     nahilalakip
    -0.86
    estacks
    -0.86
     виправивши
    -0.85
    XmlAccessType
    -0.83
    sizeCache
    -0.83
    expandindo
    -0.83
    POSITIVE LOGITS
     शुरु
    0.47
    RESET
    0.45
     hason
    0.43
    其实
    0.43
    To
    0.42
     during
    0.42
     actually
    0.40
    Actually
    0.40
     Apart
    0.40
     since
    0.40
    Activations Density 0.170%

    No Known Activations