© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4765
    Prev
    Next
    INDEX
    Explanations

    metadata and encoding specifications in text documents

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

    Character encoding (e.g., UTF, ISO)

    np_acts-logits-general · gemini-2.0-flash

    character encodings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externi
    -0.53
    Życiorys
    -0.50
     kasarigan
    -0.49
    ocuk
    -0.48
    zeciw
    -0.47
     participation
    -0.47
     présidenti
    -0.45
    پیوند
    -0.45
    tryk
    -0.45
     pottery
    -0.45
    POSITIVE LOGITS
     UTF
    0.95
    UTF
    0.88
    utf
    0.87
     encoding
    0.87
     utf
    0.86
     charset
    0.79
     Encoding
    0.73
    StandardCharsets
    0.73
    编码
    0.73
    encoding
    0.72
    Activations Density 0.192%

    No Known Activations