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. 12-GEMMASCOPE-RES-16K
    6. 16005
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "round" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.12
    évaluateur
    -1.04
     &___
    -0.96
    nonatomic
    -0.89
    Referències
    -0.89
     للمعارف
    -0.88
    QMetaType
    -0.87
    Erreferentziak
    -0.86
     createStore
    -0.85
    onOptions
    -0.84
    POSITIVE LOGITS
     ROUND
    1.39
     rounds
    1.29
     Rounds
    1.27
    round
    1.27
    Round
    1.23
    ROUND
    1.19
     Round
    1.17
     round
    1.17
    rounds
    1.17
    Rounds
    1.17
    Activations Density 0.093%

    No Known Activations