© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12658
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and structures

    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
     مرئيه
    -0.40
    fromnode
    -0.34
    nestjs
    -0.33
     IService
    -0.33
    return
    -0.32
    nextProps
    -0.32
     rospy
    -0.31
    providedIn
    -0.30
     newItem
    -0.29
    webtoken
    -0.28
    POSITIVE LOGITS
    setVerticalGroup
    0.62
     Chwiliwch
    0.62
    URLException
    0.62
     ivelany
    0.61
    SequentialGroup
    0.60
    rento
    0.57
    BagLayout
    0.57
    HideFlags
    0.57
    AccessorTable
    0.57
    atically
    0.57
    Activations Density 0.201%

    No Known Activations