© 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. 20-GEMMASCOPE-RES-16K
    6. 3626
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and their potential emotional or emphatic effects in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    emphatic statements or declarations, particularly those expressing strong personal opinions or conclusions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringRunner
    -0.44
     typelib
    -0.43
    ſt
    -0.40
    enumi
    -0.40
    település
    -0.38
     мәкал
    -0.36
    Geplaatst
    -0.35
    كويكب
    -0.35
    ขอบคุณ
    -0.34
     deposition
    -0.34
    POSITIVE LOGITS
     Domínguez
    0.53
     Trujillo
    0.51
     Dominguez
    0.51
    enough
    0.50
    adena
    0.50
    aarrggbb
    0.49
    BASEPATH
    0.49
     bloß
    0.49
    bigli
    0.48
    normal
    0.48
    Activations Density 0.193%

    No Known Activations