© 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. 453
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the validity or invalidity of claims

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

    phrases indicating disbelief or skepticism

    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
     nahilalakip
    -0.75
    OGND
    -0.56
    Hentet
    -0.55
     оригіналу
    -0.55
    RenderAtEndOf
    -0.51
     EClass
    -0.51
    Personendaten
    -0.50
    hdysval
    -0.50
     Noten
    -0.49
    ActivityCompat
    -0.48
    POSITIVE LOGITS
     anymore
    2.71
     lenger
    1.65
     längre
    1.57
     enää
    1.50
     longer
    1.49
     længere
    1.41
    longer
    1.27
     lagi
    1.25
     nữa
    1.23
     any
    1.17
    Activations Density 0.385%

    No Known Activations