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. 21-GEMMASCOPE-RES-16K
    6. 6444
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to opinions or evaluations of different subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.65
    typeorm
    -0.62
    ()")
    -0.61
     Meksiku
    -0.61
     Forumite
    -0.61
    MLLoader
    -0.61
     whereof
    -0.59
    */}
    -0.58
     referenties
    -0.58
    IndentedString
    -0.56
    POSITIVE LOGITS
     right
    2.00
    right
    1.76
     isn
    1.62
     huh
    1.58
    Right
    1.54
     Right
    1.49
     aren
    1.41
     RIGHT
    1.38
     prawda
    1.36
    Isn
    1.35
    Activations Density 0.249%

    No Known Activations