© 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. 16-GEMMASCOPE-RES-16K
    11. 14495
    Prev
    Next
    INDEX
    Explanations

    string formatting functions and their syntax in code

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

    Strings containing "String.format" or "fmt.Sprintf"

    np_acts-logits-general · gemini-2.0-flash

    string formatting

    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
    aarrggbb
    -0.91
    AsUp
    -0.78
     فريبيس
    -0.74
    VIAF
    -0.74
     onOptions
    -0.70
    DebuggerNonUser
    -0.64
     <=",
    -0.62
    StoryboardSegue
    -0.60
    principalTable
    -0.60
    LookAnd
    -0.60
    POSITIVE LOGITS
    ={`
    0.64
    Sprintf
    0.63
    numerusform
    0.56
    \{\\
    0.55
     Pulsar
    0.54
     metropolitana
    0.52
     arché
    0.51
    θηκαν
    0.51
    addCriterion
    0.51
    LEncoder
    0.51
    Activations Density 0.065%

    No Known Activations