© 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. 0-GEMMASCOPE-RES-16K
    6. 7973
    Prev
    Next
    INDEX
    Explanations

    terms related to connectivity and connections within networks or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     отношения
    -0.41
     friendship
    -0.37
     MUR
    -0.35
     createSprite
    -0.33
     PhpStorm
    -0.32
     отношений
    -0.32
    MUR
    -0.32
     useEffect
    -0.31
    iParam
    -0.31
     salvage
    -0.31
    POSITIVE LOGITS
     connected
    2.97
    connected
    2.77
     Connected
    2.63
    Connected
    2.59
     connect
    2.47
     connecting
    2.41
     connects
    2.38
     CONNECT
    2.38
    connect
    2.27
    CONNECTED
    2.25
    Activations Density 0.185%

    No Known Activations