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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73774
    Prev
    Next
    INDEX
    Explanations

    series of academic citations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    twimg
    -0.50
    WebElementEntity
    -0.49
     capucha
    -0.46
     يتيمه
    -0.44
     anún
    -0.44
     amanecer
    -0.44
     NSCoder
    -0.44
    jenigen
    -0.44
     romántico
    -0.43
    Trayectoria
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.70
    setVerticalGroup
    0.46
    CrossRef
    0.45
     citation
    0.45
    Viitteet
    0.44
    +:+
    0.44
    cited
    0.43
     studied
    0.42
    toms
    0.42
    rawDesc
    0.42
    Activations Density 0.112%

    No Known Activations