© 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. 15-GEMMASCOPE-RES-16K
    11. 2932
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation that indicate structure in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
     الحره
    -0.63
    mobileqq
    -0.62
     biß
    -0.60
    Хьажоргаш
    -0.56
     scolas
    -0.56
     []:
    -0.55
     ähn
    -0.53
    𝓻
    -0.53
    actéristi
    -0.53
    atown
    -0.52
    POSITIVE LOGITS
     –
    0.73
     ‘
    0.70
    ’
    0.69
    s
    0.66
     (‘
    0.64
    …’
    0.61
    (‘
    0.60
    neath
    0.59
    ’,
    0.59
    .’
    0.58
    Activations Density 0.538%

    No Known Activations