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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7209
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "throw" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chré
    -0.53
     Foire
    -0.51
    oreo
    -0.50
     étro
    -0.49
     paš
    -0.49
    ptes
    -0.48
     signore
    -0.47
     bonded
    -0.47
    endregion
    -0.47
     jScrollPane
    -0.47
    POSITIVE LOGITS
     thrown
    1.10
     throw
    1.04
    throws
    1.03
     throws
    1.01
     throwing
    1.00
     threw
    1.00
    thrown
    0.98
     Throwing
    0.96
     Throw
    0.95
     Throws
    0.95
    Activations Density 0.071%

    No Known Activations