© 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. 25-GEMMASCOPE-RES-16K
    11. 476
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements and formalities

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

    phrases related to feedback and confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contextLoads
    -0.65
    BeginContext
    -0.54
    placa
    -0.51
     Efq
    -0.50
     mankind
    -0.49
     people
    -0.48
     démocratie
    -0.48
     chances
    -0.47
    voi
    -0.47
    AccessorTable
    -0.47
    POSITIVE LOGITS
    ########.
    0.74
     оригіналу
    0.64
    findpost
    0.56
     onPostExecute
    0.55
    PreExecute
    0.54
     odkazy
    0.50
     незавершена
    0.50
    atoon
    0.49
    Geplaatst
    0.47
     autorytatywna
    0.46
    Activations Density 0.029%

    No Known Activations