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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 8936
    Prev
    Next
    INDEX
    Explanations

    references to keyboard functionality and user interaction with keyboards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    partements
    -0.39
     கா
    -0.36
    }}%
    -0.34
     Brut
    -0.33
     Crimin
    -0.32
    mantel
    -0.32
     bensin
    -0.31
    }})
    -0.31
     BoxFit
    -0.31
    seteq
    -0.30
    POSITIVE LOGITS
     keyboard
    1.66
     Keyboard
    1.45
    Keyboard
    1.30
    keyboard
    1.29
     keyboards
    1.26
     teclado
    1.23
    键盘
    1.20
    キーボード
    1.17
     clavier
    1.15
     клавиа
    1.13
    Activations Density 0.530%

    No Known Activations