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. 20-GEMMASCOPE-RES-16K
    6. 1401
    Prev
    Next
    INDEX
    Explanations

    code-related structures and syntax elements

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

    Parsing integers from strings

    np_acts-logits-general · gemini-2.0-flash

    parsing strings to integers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.80
    WriteBarrier
    -0.73
    SharedDtor
    -0.70
    ::_('
    -0.67
     ویکی‌پدیا
    -0.61
    istoitu
    -0.54
     препратки
    -0.53
     незавершена
    -0.53
     nahilalakip
    -0.53
    RegressionTest
    -0.52
    POSITIVE LOGITS
     parseInt
    1.29
    Integer
    1.22
    parseInt
    1.18
     Integer
    1.18
     int
    1.10
     integer
    1.08
     atoi
    1.06
    int
    1.02
    Int
    0.99
    integer
    0.99
    Activations Density 0.303%

    No Known Activations