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. 377
    Prev
    Next
    INDEX
    Explanations

    references to inclusivity and the concept of "anyone" or "anything."

    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
    )]
    
    -0.38
     bazı
    -0.36
    ))->
    -0.34
     some
    -0.32
    ie
    -0.32
     بعضی
    -0.32
    ']=$
    -0.32
    le
    -0.31
    SearchParams
    -0.30
    一些
    -0.30
    POSITIVE LOGITS
     anything
    1.48
     any
    1.48
     anyone
    1.46
    anything
    1.45
     anytime
    1.45
    Anything
    1.43
     anybody
    1.42
    anyone
    1.41
     Anything
    1.41
     ANY
    1.36
    Activations Density 0.210%

    No Known Activations