Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 85371
    Prev
    Next
    INDEX
    Explanations

    references to "stick" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    stick or sticking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.58
    dafx
    -0.58
    queryInterface
    -0.57
     Faure
    -0.50
    NameInMap
    -0.50
    fA
    -0.50
    URLException
    -0.50
     BorderRadius
    -0.50
    zA
    -0.49
     Eras
    -0.49
    POSITIVE LOGITS
     stick
    2.30
    stick
    2.19
     Stick
    2.17
    Stick
    2.11
     sticks
    1.96
     STICK
    1.89
    sticks
    1.73
     Sticks
    1.72
    STICK
    1.64
     sticking
    1.50
    Activations Density 0.005%

    No Known Activations