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

    Neuronpedia

    Jacobian LensNEW
    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. 41-GEMMASCOPE-RES-16K
    11. 9794
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to testing and understanding complex structures and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    外部リンク
    -0.44
    +#+#
    -0.36
    ]]);
    -0.36
    ]})
    -0.35
    点此举报
    -0.35
    SaveSave
    -0.35
     onOptions
    -0.35
    zzá
    -0.34
     consultato
    -0.33
    󠁴
    -0.33
    POSITIVE LOGITS
     tumor
    0.93
     protein
    0.91
     genome
    0.91
     lipid
    0.90
     chromatin
    0.89
     gene
    0.88
     soil
    0.88
     proteins
    0.88
     microbial
    0.88
     tumour
    0.88
    Activations Density 5.026%

    No Known Activations