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. 4-GEMMASCOPE-RES-16K
    6. 3473
    Prev
    Next
    INDEX
    Explanations

    references to quotes and citations 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 @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bes
    -0.58
     spett
    -0.56
    .
    -0.55
    getLogger
    -0.53
     Drury
    -0.53
    vascular
    -0.51
    sem
    -0.51
     I
    -0.51
     Anfang
    -0.50
     jTextField
    -0.50
    POSITIVE LOGITS
     quote
    2.78
    quote
    2.67
     Quote
    2.64
     quotes
    2.59
    Quote
    2.58
     QUOTE
    2.40
    Quotes
    2.30
    quotes
    2.28
     quoting
    2.26
     Quotes
    2.25
    Activations Density 0.129%

    No Known Activations