© 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. 0-GEMMASCOPE-RES-16K
    6. 8202
    Prev
    Next
    INDEX
    Explanations

    modal verbs and phrases related to verbal communication and time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])))
    -0.53
    ])).
    -0.52
     fometimes
    -0.50
    ())))
    -0.49
    ]]);
    -0.49
     Италијани
    -0.48
     }}"></
    -0.48
    )))))
    -0.48
    ()])
    -0.47
    ())));
    -0.46
    POSITIVE LOGITS
    verb
    0.64
     Christmas
    0.63
     Saturday
    0.58
    Christmas
    0.58
     weekend
    0.58
     weekends
    0.56
     Sunday
    0.56
     holidays
    0.56
     verb
    0.54
     navidad
    0.53
    Activations Density 1.578%

    No Known Activations