© 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. 3-GEMMASCOPE-RES-16K
    6. 6836
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific starting tokens, primarily to indicate the beginning of new sections or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſei
    -0.89
     beſte
    -0.84
     ſta
    -0.79
     témoig
    -0.79
    SequentialGroup
    -0.79
     ویکی‌پدی
    -0.78
    bootstrapcdn
    -0.77
     queſta
    -0.77
    ੝
    -0.76
     raiſ
    -0.73
    POSITIVE LOGITS
     referrerpolicy
    0.43
    ,
    0.33
     humanidade
    0.28
     umí
    0.26
     lecteur
    0.25
     Hälfte
    0.23
     alatt
    0.23
     bahwa
    0.23
     demais
    0.22
     Füßen
    0.22
    Activations Density 0.117%

    No Known Activations