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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53866
    Prev
    Next
    INDEX
    Explanations

    concepts related to object-oriented programming methodologies and best practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Datuak
    -0.80
    tvguidetime
    -0.67
    帖最后由
    -0.65
     الحره
    -0.60
    IsMutable
    -0.59
    +#+#
    -0.58
    AndEndTag
    -0.54
    MLLoader
    -0.54
     ExecuteAsync
    -0.51
    oredCriteria
    -0.50
    POSITIVE LOGITS
    stateMutability
    0.49
     különböz
    0.40
    Article
    0.35
     patrie
    0.35
     vál
    0.34
     dignité
    0.33
    Vale
    0.33
    mitian
    0.33
    Soc
    0.33
    SOM
    0.33
    Activations Density 0.046%

    No Known Activations