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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 28-GEMMASCOPE-RES-16K
    6. 4145
    Prev
    Next
    INDEX
    Explanations

    specific names and descriptions of characters or beings in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a comma or quotation mark

    np_acts-logits-general · gemini-2.0-flash

    technical terms and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    majánló
    -0.73
    cemment
    -0.72
     snippetHide
    -0.71
     ujednoznacz
    -0.69
    ロウィン
    -0.67
     vœ
    -0.66
     disambiguazione
    -0.65
    Хьажоргаш
    -0.64
    Woah
    -0.64
     vectorielles
    -0.61
    POSITIVE LOGITS
     hỏi
    0.31
    #
    0.31
     muß
    0.28
     unge
    0.28
    の方は
    0.27
     Thus
    0.27
     quả
    0.26
     ordered
    0.26
     thus
    0.26
     verze
    0.26
    Activations Density 0.411%

    No Known Activations