© 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. 7256
    Prev
    Next
    INDEX
    Explanations

    variables and methods related to media types and their processing within code

    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
    entibus
    -0.42
    pecially
    -0.40
    preds
    -0.38
    ibatis
    -0.38
    danh
    -0.36
    ofition
    -0.35
    tibus
    -0.34
    TITLE
    -0.34
     kayu
    -0.33
    vetor
    -0.33
    POSITIVE LOGITS
    verwijspagina
    0.92
     bezeichneter
    0.92
    rungsseite
    0.88
    expandindo
    0.84
     Савезне
    0.81
    Geplaatst
    0.80
     tartalomajánló
    0.79
    parsedMessage
    0.79
    SourceChecksum
    0.79
    extAlignment
    0.77
    Activations Density 0.620%

    No Known Activations