Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 6189
    Prev
    Next
    INDEX
    Explanations

    identifiers and naming conventions in structured data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     man
    -0.49
     a
    -0.49
    ute
    -0.48
    UTE
    -0.48
    eda
    -0.48
     Man
    -0.48
     “
    -0.47
    cas
    -0.46
    pas
    -0.46
    man
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.81
    ChromeDriver
    0.81
     wikipagina
    0.79
    WAUKEE
    0.76
    berdayakan
    0.76
    HostException
    0.75
     productName
    0.72
     itſelf
    0.72
    WebpackPlugin
    0.70
     AssemblyTitle
    0.70
    Activations Density 0.381%

    No Known Activations