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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5082
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    adaptiveStyles
    -0.87
    pecabe
    -0.81
    ésult
    -0.80
     defaultstate
    -0.80
    ंदीखरीदारी
    -0.79
     فريبيس
    -0.77
    GraphicsUnit
    -0.77
    脚注の使い方
    -0.77
    tvguidetime
    -0.74
     AssemblyCompany
    -0.74
    POSITIVE LOGITS
    s
    0.64
     and
    0.58
    [toxicity=0]
    0.57
    년
    0.54
     is
    0.53
    ︎
    0.52
     or
    0.52
     be
    0.52
    </sup>
    0.51
    }{*}{
    0.50
    Activations Density 0.745%

    No Known Activations