© 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. 1-GEMMASCOPE-RES-16K
    6. 8245
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thrown."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patent
    -0.45
    SuppressLint
    -0.44
     consult
    -0.40
    //
    -0.40
     Peace
    -0.40
    Patent
    -0.39
     patent
    -0.39
    ManagedBean
    -0.38
    BrowserRouter
    -0.37
     peace
    -0.36
    POSITIVE LOGITS
     thrown
    0.94
     threw
    0.75
    thrown
    0.71
     fingers
    0.69
    threw
    0.64
     noDo
    0.63
     sides
    0.61
     throwing
    0.60
     يتيمه
    0.60
     senses
    0.60
    Activations Density 0.151%

    No Known Activations