Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14827
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to statistical methods and estimations

    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
    mtrl
    -0.35
     alguno
    -0.34
     humanidad
    -0.34
     antigüedad
    -0.33
     either
    -0.31
     öğ
    -0.31
     intéressante
    -0.30
     penultimate
    -0.30
     Erwachsene
    -0.29
     totalidad
    -0.28
    POSITIVE LOGITS
     noDo
    0.69
    StoryboardSegue
    0.57
     kasarigan
    0.56
    GEBURTSDATUM
    0.54
     UDP
    0.52
     nakalista
    0.52
     nonUne
    0.52
    parsedMessage
    0.52
    UrlResolution
    0.52
     ſch
    0.51
    Activations Density 0.666%

    No Known Activations