© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 1660
    Prev
    Next
    INDEX
    Explanations

    terms related to participation and contribution in various contexts, including sports, healthcare, and community involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.96
     EconPapers
    -0.85
     miniaturka
    -0.84
     nakalista
    -0.84
    ьаж
    -0.81
     camiset
    -0.80
     indígen
    -0.79
     useAppContext
    -0.78
     Monfieur
    -0.75
     parachoque
    -0.74
    POSITIVE LOGITS
     the
    0.42
     and
    0.34
    .
    0.29
     to
    0.28
     are
    0.27
     will
    0.26
     of
    0.26
    ftagPool
    0.26
     who
    0.25
    esac
    0.25
    Activations Density 12.073%

    No Known Activations