© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13061
    Prev
    Next
    INDEX
    Explanations

    key programming and computing terms, particularly those related to operations and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يميديا
    -0.72
    +#+#
    -0.71
     للمعارف
    -0.66
    CloseOperation
    -0.66
    aimeJ
    -0.61
    SBATCH
    -0.60
     ſind
    -0.60
    WithIOException
    -0.60
    AnchorStyles
    -0.60
     queſta
    -0.59
    POSITIVE LOGITS
    inheritDoc
    0.32
    ↵↵
    0.31
    ėmis
    0.30
     pintada
    0.27
    <eos>
    0.27
     desarrollado
    0.27
     categoría
    0.26
     muut
    0.26
     udział
    0.26
     [*]
    0.26
    Activations Density 0.546%

    No Known Activations