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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104813
    Prev
    Next
    INDEX
    Explanations

    elements related to formatting and structure in text, such as underscores and fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    posedge
    -0.49
    EndProject
    -0.42
    OrBuilder
    -0.40
     uParam
    -0.40
     surla
    -0.40
     chi̍t
    -0.38
    ValueGenerated
    -0.37
     yyhl
    -0.36
    PreferredItem
    -0.35
     <>",
    -0.35
    POSITIVE LOGITS
    дарь
    0.61
     typelib
    0.51
    KommentareTeilen
    0.49
     Normdatei
    0.47
    richTextPanel
    0.44
     navideña
    0.43
    PointerException
    0.43
    assies
    0.43
     fä
    0.42
    下载附件
    0.42
    Activations Density 0.068%

    No Known Activations