© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 115114
    Prev
    Next
    INDEX
    Explanations

    instances of the word "throw" and its various forms or related phrases

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

    action of throwing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pgsql
    -0.56
    AndEndTag
    -0.54
    دانشنامهٔ
    -0.54
    ECI
    -0.53
    copyOf
    -0.52
    Personendaten
    -0.52
    LayoutConstraint
    -0.51
    CPtr
    -0.51
    tableFuture
    -0.50
     kasarigan
    -0.50
    POSITIVE LOGITS
    throw
    1.20
     throw
    1.16
     Throw
    1.05
    Throw
    1.03
     throwing
    0.96
     thrown
    0.88
    throwing
    0.88
    Throwing
    0.86
     threw
    0.85
    thrown
    0.84
    Activations Density 0.014%

    No Known Activations