© 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. 1772
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or statistical methodologies

    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
     kaynağından
    -0.50
    ())))
    -0.50
    روابط
    -0.50
    almaz
    -0.50
     Lors
    -0.49
    principalColumn
    -0.48
    Enllaces
    -0.48
    ecken
    -0.47
    るま
    -0.47
    ())){
    -0.47
    POSITIVE LOGITS
     Pt
    0.56
    transQ
    0.53
    indd
    0.49
    Toole
    0.49
    opropyl
    0.48
    SUP
    0.47
     sopp
    0.46
     SUP
    0.46
    Pt
    0.46
    Part
    0.46
    Activations Density 0.168%

    No Known Activations