© 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. 12-GEMMASCOPE-RES-16K
    6. 13857
    Prev
    Next
    INDEX
    Explanations

    instances of the word "new" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
     Winaray
    -0.69
    RemindMe
    -0.58
    ceptre
    -0.56
     Forumite
    -0.54
     AssemblyCompany
    -0.53
     getRole
    -0.52
    UrlResolution
    -0.51
     courseId
    -0.50
    CodeDom
    -0.50
     sillas
    -0.49
    POSITIVE LOGITS
     New
    1.57
     new
    1.52
    New
    1.47
    new
    1.40
     NEW
    1.35
    NEW
    1.22
    新
    1.08
     neuen
    1.05
     Nuevas
    1.03
     nieuwe
    1.01
    Activations Density 0.148%

    No Known Activations