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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3318
    Prev
    Next
    INDEX
    Explanations

    references to metadata and timestamps in an article or post

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

    Signatures, dates, or social media posts

    np_acts-logits-general · gemini-2.0-flash

    posted at date and time

    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
    ########.
    -0.68
     يتيمه
    -0.62
    -------------</
    -0.59
    oredCriteria
    -0.56
    ChildScrollView
    -0.53
     تانيه
    -0.52
    WebElementEntity
    -0.51
     ddelweddau
    -0.51
    mybatisplus
    -0.50
    المكان
    -0.49
    POSITIVE LOGITS
     Tapatalk
    0.57
    consulté
    0.50
    menuStrip
    0.48
    indd
    0.46
    apatalk
    0.44
    发表于
    0.44
     Pingback
    0.40
    VIAF
    0.40
     Abgerufen
    0.40
    Reply
    0.40
    Activations Density 0.299%

    No Known Activations