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. 23-GEMMASCOPE-RES-131K
    6. 37
    Prev
    Next
    INDEX
    Explanations

    conversations surrounding social and political issues, particularly those related to rights and healthcare

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     squ
    -0.37
    ="@+
    -0.35
    PerformLayout
    -0.35
     Hame
    -0.35
    xodo
    -0.34
     useContext
    -0.34
     sli
    -0.33
     wireless
    -0.33
    topt
    -0.33
    topus
    -0.32
    POSITIVE LOGITS
    principalColumn
    0.57
     secular
    0.57
    RTEX
    0.53
     disambiguazione
    0.49
     NSError
    0.48
     cytometry
    0.48
     SDLK
    0.47
     INTERESAR
    0.47
    bootstrapcdn
    0.46
    ativistic
    0.46
    Activations Density 0.065%

    No Known Activations