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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 38780
    Prev
    Next
    INDEX
    Explanations

    references to conflicts and power struggles involving groups in the Middle East and Africa

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     bouteille
    -0.43
    Student
    -0.36
     beautiful
    -0.34
    엑
    -0.34
     Grecs
    -0.33
     güzel
    -0.33
    smarty
    -0.32
    Star
    -0.31
     Student
    -0.31
    leven
    -0.31
    POSITIVE LOGITS
     estekak
    0.61
    ValueStyle
    0.52
    rungsseite
    0.52
    ponses
    0.51
    ématiques
    0.51
     deadliest
    0.48
    cotch
    0.48
     poveznice
    0.47
    RTCK
    0.45
    ouflage
    0.45
    Activations Density 0.026%

    No Known Activations