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. 3-GEMMASCOPE-RES-16K
    6. 12833
    Prev
    Next
    INDEX
    Explanations

    phrases related to built-in components or features in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.52
    istiwa
    -0.49
    \]
    -0.46
    consulté
    -0.45
     toss
    -0.45
     Inscrivez
    -0.45
     surnames
    -0.44
     rojos
    -0.44
     qualifying
    -0.44
     urma
    -0.43
    POSITIVE LOGITS
     embedded
    1.14
    embedded
    0.98
     resourceCulture
    0.95
     embed
    0.90
     embedding
    0.88
    WriteTagHelper
    0.86
     Embedded
    0.86
    Embedded
    0.82
    bootstrapcdn
    0.79
    aarrggbb
    0.78
    Activations Density 0.363%

    No Known Activations