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. 10-GEMMASCOPE-RES-16K
    6. 2946
    Prev
    Next
    INDEX
    Explanations

    starting phrases or key terms that indicate the beginning of a new section or topic in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aranja
    -0.47
    رو
    -0.46
    emes
    -0.45
    xer
    -0.45
    列
    -0.45
     Consult
    -0.45
    mande
    -0.45
     tendría
    -0.44
    ‍
    -0.43
    zam
    -0.43
    POSITIVE LOGITS
    WithIOException
    1.11
     propOrder
    1.05
    HasAnnotation
    1.03
    rrggbb
    0.88
    ंदीखरीदारी
    0.83
     незавершена
    0.83
    queryInterface
    0.81
    DebuggerNonUser
    0.81
     betweenstory
    0.80
     Efq
    0.80
    Activations Density 1.844%

    No Known Activations