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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 106
    Prev
    Next
    INDEX
    Explanations

    references to financial markets and stock exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    academic and technical document details like references, citations, and institutional information.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    󠁢
    -0.44
     bedo
    -0.42
     meth
    -0.41
     roommates
    -0.40
     Hook
    -0.38
     tribal
    -0.38
    currentThread
    -0.38
    vonne
    -0.38
     optim
    -0.37
    حوالہ
    -0.36
    POSITIVE LOGITS
    pexpr
    0.64
     CiNii
    0.51
    Autoritní
    0.50
    庁
    0.49
    twimg
    0.47
    Erreferentziak
    0.46
    providedIn
    0.43
    UseVisualStyle
    0.42
    MessageWindow
    0.42
    tagHelperRunner
    0.41
    Activations Density 1.548%

    No Known Activations