© 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. 965
    Prev
    Next
    INDEX
    Explanations

    the presence of access modifiers in code, particularly "public" and "private"

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

    Followed by "function"

    np_acts-logits-general · gemini-2.0-flash

    public function

    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
     ligiloj
    -0.78
     HasFactory
    -0.75
     kasarigan
    -0.75
     pinulongan
    -0.72
    InteropServices
    -0.71
    ContentAsync
    -0.70
    enumi
    -0.69
    PreferredItem
    -0.69
     Parcelable
    -0.69
    hoeddwyd
    -0.67
    POSITIVE LOGITS
     function
    0.84
    function
    0.63
     Function
    0.59
     Ανακτήθηκε
    0.55
    Function
    0.52
    funktion
    0.51
    函数
    0.51
     action
    0.50
    unction
    0.50
    Action
    0.49
    Activations Density 0.037%

    No Known Activations