© 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. 13-GEMMASCOPE-RES-16K
    6. 8698
    Prev
    Next
    INDEX
    Explanations

    terms related to cursor and mouse interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reg
    -0.44
     distinctive
    -0.42
     BOP
    -0.42
    Resist
    -0.40
     building
    -0.40
    DidLoad
    -0.40
    积
    -0.40
    làm
    -0.39
     MCM
    -0.39
     Wod
    -0.39
    POSITIVE LOGITS
     cursor
    1.18
    cursor
    1.13
    Cursor
    1.12
     Cursor
    1.08
     pointer
    1.05
     mouse
    1.02
     Mouse
    1.00
    Pointer
    0.97
    Mouse
    0.96
     MOUSE
    0.96
    Activations Density 0.179%

    No Known Activations