© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5803
    Prev
    Next
    INDEX
    Explanations

    elements related to modal verbs and expressions of potentiality or obligation

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

    Non-English programming or markup code

    np_acts-logits-general · gemini-2.0-flash

    non-english words

    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
     getInt
    -0.40
     posX
    -0.39
     conmigo
    -0.38
    кож
    -0.38
    retudo
    -0.37
     nullptr
    -0.37
     laikā
    -0.37
     strå
    -0.37
    vician
    -0.37
    entieth
    -0.36
    POSITIVE LOGITS
    +#+#
    0.55
    قایناق‌لار
    0.53
    httphttps
    0.53
     AssemblyProduct
    0.52
    ंदीखरीदारी
    0.51
    Portale
    0.50
     EconPapers
    0.47
     FetchType
    0.47
     aufzu
    0.46
     Վերցված
    0.46
    Activations Density 0.237%

    No Known Activations