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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6136
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to data analysis and modeling techniques

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

    Data fitting to curves or lines

    np_acts-logits-general · gemini-2.0-flash

    fitting models and curves

    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
     consultato
    -0.77
     nakalista
    -0.55
    ManagedBean
    -0.55
    icose
    -0.54
    NewGuid
    -0.54
    WaitGroup
    -0.53
    PointerException
    -0.53
    CppCodeGen
    -0.52
     Totem
    -0.52
    reonine
    -0.52
    POSITIVE LOGITS
     fit
    1.08
     curve
    1.00
     fits
    0.99
     fitting
    0.98
     fitted
    0.98
    fit
    0.97
    fitted
    0.93
     Fitting
    0.90
    Fit
    0.89
    Fitting
    0.89
    Activations Density 1.369%

    No Known Activations