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 - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 371
    Prev
    Next
    INDEX
    Explanations

    terms related to file importing and exporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setOnAction
    -0.43
    DebuggerNonUser
    -0.42
     given
    -0.41
     band
    -0.40
    anneer
    -0.40
     عق
    -0.40
    illères
    -0.39
    hance
    -0.39
    Personendaten
    -0.39
     toughest
    -0.39
    POSITIVE LOGITS
     import
    1.91
     Import
    1.88
     importing
    1.79
     imported
    1.78
     imports
    1.77
     importation
    1.75
    Import
    1.70
     Importing
    1.70
     Imports
    1.60
     importación
    1.58
    Activations Density 0.122%

    No Known Activations