© 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. 25-GEMMASCOPE-RES-16K
    11. 15137
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols that indicate questions or exclamations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.83
     autorytatywna
    -0.79
     Administrativna
    -0.77
    :✨
    -0.77
     فريبيس
    -0.68
    Datuak
    -0.68
     createSprite
    -0.67
     يتيمه
    -0.67
     незавершена
    -0.67
     صوتيه
    -0.66
    POSITIVE LOGITS
    ↵↵
    0.61
    ↵
    0.43
    ↵↵↵
    0.42
    </h3>
    0.41
    </i>
    0.40
    </b>
    0.39
    </strong>
    0.37
    ?”
    0.36
    </em>
    0.36
    </h4>
    0.35
    Activations Density 0.077%

    No Known Activations