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. 130940
    Prev
    Next
    INDEX
    Explanations

    URLs and hyperlinks

    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
     queſta
    -1.09
    ſelves
    -0.89
     ſche
    -0.87
    parsedMessage
    -0.87
     ſind
    -0.83
     ſch
    -0.82
     ſta
    -0.82
     pleaſure
    -0.81
     $_(
    -0.81
     يتيمه
    -0.81
    POSITIVE LOGITS
    ://
    0.48
    https
    0.46
    http
    0.45
    :
    0.44
     http
    0.42
    The
    0.42
     https
    0.38
    s
    0.38
    <strong>
    0.36
      
    0.36
    Activations Density 0.003%

    No Known Activations