© 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. 20-GEMMASCOPE-RES-16K
    11. 4351
    Prev
    Next
    INDEX
    Explanations

    actions involving "throwing" or "discarding" items

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

    phrases involving throwing or discarding something.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    AndEndTag
    -0.65
     Administrativna
    -0.59
    دانشنامهٔ
    -0.58
     kasarigan
    -0.56
     nakalista
    -0.55
    клопе
    -0.55
    LayoutConstraint
    -0.54
    rungsseite
    -0.53
     Numerade
    -0.53
     informée
    -0.53
    POSITIVE LOGITS
    throw
    1.24
     throw
    1.23
     Throw
    1.08
    Throw
    1.05
     throwing
    1.01
     thrown
    0.91
    Throwing
    0.89
    throwing
    0.88
     Throwing
    0.87
     threw
    0.86
    Activations Density 0.075%

    No Known Activations