© 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. 14-GEMMASCOPE-RES-16K
    11. 8439
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming or server configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.95
     Administrativna
    -0.92
    fromnode
    -0.85
    GEBURTSDATUM
    -0.83
     Италијани
    -0.81
    Autoritní
    -0.79
    transQ
    -0.78
    oredCriteria
    -0.75
    endphp
    -0.75
     CanadaChoose
    -0.74
    POSITIVE LOGITS
     
    0.44
     silently
    0.39
     very
    0.38
     Lem
    0.38
     silent
    0.37
     [],
    0.37
     Ham
    0.37
    ↵↵
    0.36
     compressed
    0.35
     materi
    0.35
    Activations Density 0.590%

    No Known Activations