© 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. 11086
    Prev
    Next
    INDEX
    Explanations

    elements related to documentation and system errors

    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
    Geplaatst
    -0.68
    ########.
    -0.51
     ktorí
    -0.51
    Manbalar
    -0.49
    énario
    -0.48
    CodedInputStream
    -0.47
    .*")]
    -0.46
    ValueStyle
    -0.46
     them
    -0.45
     Ubicación
    -0.45
    POSITIVE LOGITS
     des
    1.44
     der
    1.16
     eines
    0.97
     unseres
    0.95
     ihres
    0.91
     von
    0.87
     seines
    0.87
     Ihres
    0.84
     mehrerer
    0.84
     unserer
    0.81
    Activations Density 0.089%

    No Known Activations