© 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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 10919
    Prev
    Next
    INDEX
    Explanations

    references to vigorous actions or descriptions related to cellular structures and biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fetchone
    -0.40
    mimetype
    -0.39
     sumpay
    -0.38
     cheap
    -0.36
     almend
    -0.35
    usermodel
    -0.34
    tanleria
    -0.34
    Brainz
    -0.34
    ziplin
    -0.34
     replaced
    -0.33
    POSITIVE LOGITS
    ViewFeatures
    0.69
     BrowserModule
    0.67
     spher
    0.63
    Globe
    0.60
     horiz
    0.60
    spher
    0.59
     CommonModule
    0.58
     Spherical
    0.58
     spherical
    0.57
    verwijspagina
    0.56
    Activations Density 1.739%

    No Known Activations