© 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. 2-GEMMASCOPE-RES-16K
    6. 8210
    Prev
    Next
    INDEX
    Explanations

    references to information retrieval or data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Préparation
    -0.38
     Partagez
    -0.35
    Royaume
    -0.34
     批量
    -0.32
    DDG
    -0.32
    CHAPTER
    -0.32
    Einen
    -0.31
     Bry
    -0.31
    studentId
    -0.30
    Fernseh
    -0.30
    POSITIVE LOGITS
     info
    3.44
     Info
    3.25
    info
    3.13
    Info
    3.03
     INFO
    2.83
    INFO
    2.70
     information
    2.53
     infos
    2.53
     Information
    2.38
     INFORMATION
    2.22
    Activations Density 0.104%

    No Known Activations