© 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. 13313
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and syntax

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

    Tokens before arguments/parameters

    np_acts-logits-general · gemini-2.0-flash

    function, method, and parameter names

    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
     Title
    -0.44
     sper
    -0.42
    ktop
    -0.41
    gaz
    -0.41
    Title
    -0.41
    verture
    -0.41
     R
    -0.39
    WriteLine
    -0.38
    OneToMany
    -0.38
     معد
    -0.38
    POSITIVE LOGITS
    Geplaatst
    0.89
    GEBURTSDATUM
    0.88
     houſe
    0.88
     Houſe
    0.86
     CreateTagHelper
    0.80
     itſelf
    0.78
     uſ
    0.78
     initComponents
    0.77
     purpoſe
    0.76
     ſhe
    0.75
    Activations Density 0.405%

    No Known Activations