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. 3-GEMMASCOPE-RES-16K
    6. 15999
    Prev
    Next
    INDEX
    Explanations

    terms related to contracts, agreements, and business dealings

    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
    tonode
    -0.63
    OGND
    -0.62
     GenerationType
    -0.57
    GraphicsUnit
    -0.56
     Meksiku
    -0.56
    enumi
    -0.56
    wpi
    -0.55
     Мексичка
    -0.53
    reportWebVitals
    -0.53
     StyleSheet
    -0.52
    POSITIVE LOGITS
    fjspx
    0.61
    AsUp
    0.55
    CompilerServices
    0.54
    NOPQRST
    0.52
    ']));
    0.51
    গ্রহ
    0.50
    icato
    0.49
    ειν
    0.48
    lasty
    0.47
    RegressionTest
    0.47
    Activations Density 1.307%

    No Known Activations