© 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. 9-GEMMASCOPE-RES-16K
    11. 8681
    Prev
    Next
    INDEX
    Explanations

    technical parameters and attributes commonly used in URLs and web references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Щ
    -0.29
    ERT
    -0.29
     مد
    -0.29
    ler
    -0.28
     medi
    -0.28
    libft
    -0.28
    ert
    -0.28
     Enti
    -0.28
    Ao
    -0.27
    Cd
    -0.26
    POSITIVE LOGITS
    DockStyle
    0.88
     betweenstory
    0.83
    fromnode
    0.75
    ftagPool
    0.73
    aarrggbb
    0.73
    transQ
    0.72
     فريبيس
    0.72
     CascadeType
    0.71
    bitField
    0.71
    rungsseite
    0.70
    Activations Density 0.288%

    No Known Activations