© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 8832
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "throw" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.74
     nakalista
    -0.71
    parsedMessage
    -0.69
     kasarigan
    -0.69
    mybatisplus
    -0.67
    Personendaten
    -0.65
    IsMutable
    -0.65
    styleType
    -0.64
     صوتيه
    -0.63
     snippetHide
    -0.63
    POSITIVE LOGITS
    throw
    1.07
     throw
    1.07
     Throw
    0.90
    Throw
    0.90
     throwing
    0.86
    Throwing
    0.76
     throws
    0.75
    throwing
    0.74
     thrown
    0.73
    throws
    0.73
    Activations Density 0.197%

    No Known Activations