© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 13178
    Prev
    Next
    INDEX
    Explanations

    phrases related to support and recommendations

    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
    BagConstraints
    -0.90
    principalColumn
    -0.80
    noinspection
    -0.74
     fucked
    -0.70
    spoiler
    -0.70
    ftagPool
    -0.66
     
    -0.66
     bastard
    -0.66
     TextInputType
    -0.65
    substack
    -0.65
    POSITIVE LOGITS
     ifade
    0.56
    فایل‌لار
    0.51
     hänen
    0.49
     Réponses
    0.48
     karde
    0.47
    expandindo
    0.45
     our
    0.44
     dolayı
    0.44
     vediamo
    0.43
    şiv
    0.42
    Activations Density 0.161%

    No Known Activations