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. 11-GEMMASCOPE-RES-16K
    6. 6021
    Prev
    Next
    INDEX
    Explanations

    verbs related to approval or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.63
    HasForeignKey
    -0.61
    脚注の使い方
    -0.58
    ScopeManager
    -0.57
     hefyd
    -0.55
    gway
    -0.54
    Vedi
    -0.53
    mapStateToProps
    -0.52
    хіво
    -0.52
     насељу
    -0.52
    POSITIVE LOGITS
    tahui
    0.50
    org
    0.49
     때문
    0.48
    :].
    0.47
     Binghamton
    0.46
     inwoners
    0.46
     Agnew
    0.45
    Newswire
    0.45
    ba
    0.45
    ことです
    0.44
    Activations Density 0.746%

    No Known Activations