© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 498
    Prev
    Next
    INDEX
    Explanations

    elements of mathematical notation related to functions and transformations in theoretical physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.61
    ContextHolder
    -0.51
    ]]
    -0.50
     kasarigan
    -0.49
    }>
    -0.48
    taj
    -0.48
    »
    -0.46
    ».
    -0.46
     Adieu
    -0.46
    قام
    -0.45
    POSITIVE LOGITS
    cline
    0.90
    tvguidetime
    0.85
    הערות
    0.66
     nahilalakip
    0.66
    følgelig
    0.65
    Personensuche
    0.65
    monials
    0.65
     defaultstate
    0.64
     $_"
    0.63
    ſelves
    0.63
    Activations Density 0.063%

    No Known Activations