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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 4735
    Prev
    Next
    INDEX
    Explanations

    instances of specific time references or moments within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.70
    MockMvc
    -0.55
    באנגלית
    -0.54
    ragamo
    -0.53
    irited
    -0.53
    CONSIN
    -0.52
    XmlAccessType
    -0.51
    parian
    -0.51
    erees
    -0.50
    bardier
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.65
    tagHelperRunner
    0.64
     worst
    0.60
    At
    0.59
    {§
    0.59
     الحره
    0.59
     at
    0.56
     At
    0.54
     nowhere
    0.54
    worst
    0.53
    Activations Density 0.117%

    No Known Activations