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. 21-GEMMASCOPE-RES-16K
    6. 7755
    Prev
    Next
    INDEX
    Explanations

    instances of variation in language and tone, reflecting a casual or informal style

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    égration
    -0.36
     efectivamente
    -0.31
     Bühne
    -0.31
     intégrée
    -0.31
     castigo
    -0.31
    either
    -0.30
    rangian
    -0.30
     either
    -0.30
     automatiques
    -0.30
    чти
    -0.29
    POSITIVE LOGITS
    einf
    0.70
     plain
    0.68
     Plain
    0.67
    Plain
    0.66
     simply
    0.64
    styleType
    0.62
     חיצוניים
    0.61
     general
    0.60
    saraba
    0.60
     Exacts
    0.59
    Activations Density 0.427%

    No Known Activations