© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5279
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and representations of scientific computations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.69
     }}\
    -0.61
     }\
    -0.59
     }}$
    -0.57
     }}}
    -0.56
     }}{
    -0.56
     Chat
    -0.56
     }}^{\
    -0.56
    
    -0.56
     }},
    -0.55
    POSITIVE LOGITS
     fédé
    0.42
     fallu
    0.42
     auroit
    0.42
     ocupación
    0.41
     générale
    0.40
     savait
    0.39
     felicitación
    0.38
     Construcción
    0.38
     fallait
    0.38
     Compañía
    0.37
    Activations Density 0.086%

    No Known Activations