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. 62233
    Prev
    Next
    INDEX
    Explanations

    assembly attributes and their related details

    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
     betweenstory
    -0.50
     fleuve
    -0.47
     MainAxisSize
    -0.47
     lecz
    -0.43
     doInBackground
    -0.42
     pouvoit
    -0.41
    SqlClient
    -0.40
    CodedInputStream
    -0.39
     auroit
    -0.39
     étoit
    -0.39
    POSITIVE LOGITS
    Билгалдахарш
    0.68
    :
    0.59
    GEBURTSDATUM
    0.56
    Hentet
    0.52
    setopt
    0.52
     AssemblyCulture
    0.51
    staticmethod
    0.51
     للاسماء
    0.50
    Demografie
    0.47
     Jungle
    0.47
    Activations Density 0.002%

    No Known Activations