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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8037
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to software development and version control in Unity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entera
    -0.29
    。
    -0.29
     obligado
    -0.28
     apropiado
    -0.27
     mayoría
    -0.27
     correspondiente
    -0.26
     solución
    -0.25
     povin
    -0.25
    ,
    -0.24
    jąca
    -0.24
    POSITIVE LOGITS
     للاسماء
    1.11
    ValueStyle
    1.06
     houſe
    1.03
     queſta
    1.02
     faſt
    1.02
     مشين
    1.01
     snippetHide
    1.00
     ब्रेकडाउन
    1.00
    parsedMessage
    0.99
     ſte
    0.99
    Activations Density 0.348%

    No Known Activations