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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 41
    Prev
    Next
    INDEX
    Explanations

    elements of code or programming-related syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     engraçadas
    -0.62
     SBS
    -0.57
     uſe
    -0.57
    ettare
    -0.56
     bezeichneter
    -0.56
     absc
    -0.55
     fusca
    -0.55
     Estim
    -0.55
    álja
    -0.54
    Jîn
    -0.54
    POSITIVE LOGITS
     autorytatywna
    0.81
    onAttach
    0.74
    UrlResolution
    0.60
    tagHelperRunner
    0.59
    XtraReports
    0.58
    BASELINE
    0.55
    MessageOf
    0.54
    XtraGrid
    0.54
     חיצוניים
    0.53
    Unmarshal
    0.53
    Activations Density 0.163%

    No Known Activations