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. 20-GEMMASCOPE-RES-16K
    6. 1205
    Prev
    Next
    INDEX
    Explanations

    names and titles related to characters and entities in fictional contexts

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

    Characters or strings after a mathematical symbol

    np_acts-logits-general · gemini-2.0-flash

    Kirby presented, Andersen terminated, Century Exploration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.68
     AssemblyTitle
    -0.67
    rungsseite
    -0.67
    oa̍t
    -0.60
     ProtoMessage
    -0.57
    <?
    -0.57
     المعيارى
    -0.56
    UrlResolution
    -0.56
     يتيمه
    -0.55
     Wikimedijinoj
    -0.55
    POSITIVE LOGITS
     prescribed
    0.35
    viewBox
    0.35
    RequiresApi
    0.34
    SupportActionBar
    0.32
    Deployment
    0.32
    mybatisplus
    0.31
    ACHUSET
    0.31
    FIXED
    0.30
    DBNull
    0.30
    ニク
    0.30
    Activations Density 1.468%

    No Known Activations