© 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. 12-GEMMASCOPE-RES-16K
    6. 10364
    Prev
    Next
    INDEX
    Explanations

    personal opinions and subjective statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gameserver
    -0.71
     nakalista
    -0.70
    brainly
    -0.66
     Superhosts
    -0.65
    ContentAlignment
    -0.65
    fjspx
    -0.64
     <>",
    -0.64
    ","");
    -0.62
     disambiguazione
    -0.61
     Baillargeon
    -0.61
    POSITIVE LOGITS
    EndContext
    0.48
    WebVitals
    0.46
    expandindo
    0.44
    WebMethod
    0.43
    tapa
    0.42
    gdx
    0.42
     appunto
    0.42
     only
    0.42
    xically
    0.41
     apple
    0.41
    Activations Density 0.515%

    No Known Activations