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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6638
    Prev
    Next
    INDEX
    Explanations

    instances of first-person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -1.41
     
    -1.37
     a
    -1.33
     the
    -1.30
     in
    -1.28
    -
    -1.21
     and
    -1.20
     of
    -1.20
     to
    -1.14
     an
    -1.13
    POSITIVE LOGITS
     myſelf
    2.47
     Monfieur
    2.01
     Efq
    1.96
     itſelf
    1.84
     pleaſure
    1.75
     Theſe
    1.74
     doubtnut
    1.72
     ―――――
    1.72
    ^(@)
    1.72
     auffi
    1.68
    Activations Density 0.454%

    No Known Activations