© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13034
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" along with other prepositions and minor content words

    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
    enumi
    -0.33
    ownerId
    -0.32
     незавершена
    -0.30
    ://
    -0.29
    Các
    -0.29
    足够
    -0.27
    被称为
    -0.27
    ̲
    -0.27
     smrti
    -0.27
     कैसी
    -0.26
    POSITIVE LOGITS
    rungsseite
    0.65
    хьтан
    0.59
    mybatisplus
    0.57
    complexContent
    0.57
     intptr
    0.57
     tiguan
    0.54
    pushFollow
    0.54
    zzano
    0.52
    WriteLiteral
    0.51
    SpringBootTest
    0.51
    Activations Density 1.027%

    No Known Activations