© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2668
    Prev
    Next
    INDEX
    Explanations

    references to the word "ma" and its variations in different contexts

    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
    mobileqq
    -0.65
    tamol
    -0.60
     henvisninger
    -0.52
     situ
    -0.50
    DotNetBar
    -0.50
    spection
    -0.49
     Wikimédia
    -0.49
     validity
    -0.47
    Билгалдахарш
    -0.46
     <<<<<<<<<<<<<<
    -0.46
    POSITIVE LOGITS
     оригіналу
    0.56
    ufact
    0.49
    Diweddarwch
    0.47
    uxxxx
    0.47
    ConstraintMaker
    0.47
     Intent
    0.46
     soeur
    0.46
    eve
    0.44
    thews
    0.44
     trận
    0.44
    Activations Density 0.135%

    No Known Activations