© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 13100
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to licensing and permissions

    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
     itſelf
    -0.54
     themſelves
    -0.49
     becauſe
    -0.48
     greateſt
    -0.47
     pleaſure
    -0.46
     againſt
    -0.46
     himſelf
    -0.45
     Efq
    -0.45
     raiſ
    -0.44
     Theſe
    -0.44
    POSITIVE LOGITS
    UserScript
    0.29
     définiti
    0.25
    GEBURTSDATUM
    0.24
    ConstraintMaker
    0.23
    rungsseite
    0.23
     vícti
    0.23
    號
    0.23
     ivelany
    0.23
    銀
    0.22
    階級
    0.22
    Activations Density 3.745%

    No Known Activations