© 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. 8353
    Prev
    Next
    INDEX
    Explanations

    comparisons involving numerical limits or thresholds

    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
     franquicia
    -0.35
     scientifique
    -0.35
     avocat
    -0.34
     multitud
    -0.33
     Fútbol
    -0.33
     Wissenschaft
    -0.32
    AppComponent
    -0.31
     Russie
    -0.31
     olmaz
    -0.31
    Name
    -0.30
    POSITIVE LOGITS
     <=
    1.18
    )<=
    1.05
    <=
    1.02
    leq
    1.00
    ]<=
    0.98
     ≤
    0.92
    ≤
    0.91
    leqslant
    0.90
    ⩽
    0.81
    leqq
    0.79
    Activations Density 0.197%

    No Known Activations