© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 9020
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.90
     purpoſe
    -0.89
     незавершена
    -0.89
     reaſon
    -0.86
     greateſt
    -0.85
     ſeveral
    -0.84
     HttpNotFound
    -0.83
     GenerationType
    -0.83
     Houſe
    -0.83
     itſelf
    -0.82
    POSITIVE LOGITS
     po
    0.50
     “
    0.47
    ha
    0.46
    po
    0.46
     con
    0.45
    stav
    0.45
     sa
    0.44
     ag
    0.43
     Po
    0.43
     tu
    0.43
    Activations Density 0.408%

    No Known Activations