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

    Neuronpedia

    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. 22-GEMMASCOPE-RES-16K
    11. 6311
    Prev
    Next
    INDEX
    Explanations

    gerunds and adjectives that denote actions or characteristics in medical and scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reconnect
    -0.33
     other
    -0.32
     ACTUAL
    -0.28
    meta
    -0.28
    reibung
    -0.27
     други
    -0.26
     спа
    -0.26
    updated
    -0.25
     together
    -0.25
     annet
    -0.25
    POSITIVE LOGITS
     nonUne
    0.76
    IntoConstraints
    0.72
     للاسماء
    0.71
     BoxFit
    0.69
     AssemblyTitle
    0.67
    transQ
    0.66
     oprot
    0.65
    __(/*!
    0.64
    featureID
    0.62
    Aholisi
    0.61
    Activations Density 0.668%

    No Known Activations