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. 21-GEMMASCOPE-RES-16K
    6. 12561
    Prev
    Next
    INDEX
    Explanations

    specific phrases or expressions that refer to time or measurement events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $_['
    -0.54
    AspNet
    -0.54
    MessageTagHelper
    -0.45
    ViewImports
    -0.45
    ImageField
    -0.45
    ifax
    -0.45
    Décès
    -0.44
     insuffisamment
    -0.43
    '][$
    -0.43
    ViewFeatures
    -0.42
    POSITIVE LOGITS
     minutes
    2.60
     minute
    2.51
    minute
    2.18
     Minutes
    2.12
    minutes
    2.09
     seconds
    2.08
    Minutes
    1.96
     Minute
    1.96
     moment
    1.93
     moments
    1.93
    Activations Density 0.812%

    No Known Activations