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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3381
    Prev
    Next
    INDEX
    Explanations

    key medical terms and concepts related to understanding and investigation in treatment contexts

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

    preceding "of," "in," or "between"

    np_acts-logits-general · gemini-2.0-flash

    study and understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ContentValues
    -0.46
     utafitiHapana
    -0.43
    новниш
    -0.40
    Fatalf
    -0.39
    RenderAtEndOf
    -0.39
    styleUrls
    -0.39
    Soorten
    -0.38
    huana
    -0.38
    ksikon
    -0.38
     <>",
    -0.37
    POSITIVE LOGITS
    mybatisplus
    0.44
     mắn
    0.43
     newOwner
    0.43
    Car
    0.42
    lifter
    0.42
     Realität
    0.41
    ACF
    0.40
    şu
    0.40
    neighbour
    0.40
    Cry
    0.40
    Activations Density 1.503%

    No Known Activations