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. 12-GEMMASCOPE-RES-16K
    6. 4306
    Prev
    Next
    INDEX
    Explanations

    instances of the word "throw" and its variations 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 @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    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
    -0.81
     grotte
    -0.79
     scolaires
    -0.76
     particulières
    -0.74
    behörde
    -0.74
    essentiel
    -0.73
     huellas
    -0.73
     متعلقه
    -0.72
    diale
    -0.71
    ADEL
    -0.71
    POSITIVE LOGITS
     throw
    1.67
     Throw
    1.46
     throwing
    1.45
     throws
    1.44
     threw
    1.40
     thrown
    1.40
    throwing
    1.32
    Throw
    1.31
     Throws
    1.26
    throws
    1.26
    Activations Density 0.152%

    No Known Activations