Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8489
    Prev
    Next
    INDEX
    Explanations

    references to historical events, particularly related to specific years or significant changes

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

    Years in the 1800s (e.g., 1850, 1863)

    np_acts-logits-general · gemini-2.0-flash

    numbers in the 1800s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.65
    !*\
    -0.63
    RoutingModule
    -0.57
    ----</
    -0.57
    ódz
    -0.55
    appé
    -0.51
     مواليد
    -0.50
    ècie
    -0.50
     initComponents
    -0.50
    DNEY
    -0.49
    POSITIVE LOGITS
    +#+#
    0.67
     Monfieur
    0.56
    ſelves
    0.56
    ReusableCell
    0.56
     Família
    0.52
    Editable
    0.52
    borderSide
    0.51
     صوتيه
    0.51
     Majefty
    0.51
     poupée
    0.51
    Activations Density 0.068%

    No Known Activations