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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16183
    Prev
    Next
    INDEX
    Explanations

    programming functions and methods related to parsing numbers and strings

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

    Parsing strings to numbers

    np_acts-logits-general · gemini-2.0-flash

    parsing numbers from text

    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
    >",
    -0.71
     resourceCulture
    -0.71
    Datuak
    -0.70
    scalatest
    -0.69
    IsContent
    -0.69
     '*')
    -0.66
    <>("
    -0.64
    Identyfik
    -0.64
    }*/
    -0.64
    AutoScaleMode
    -0.62
    POSITIVE LOGITS
    dotenv
    0.58
     AspNetCore
    0.53
    LElement
    0.50
    ContextCompat
    0.50
     Palestina
    0.45
    parseDouble
    0.45
     TableColumn
    0.44
    URIComponent
    0.44
     Jost
    0.43
     Socialista
    0.43
    Activations Density 0.052%

    No Known Activations