© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 7563
    Prev
    Next
    INDEX
    Explanations

    numeric values and variable identifiers commonly used in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    `]
    -0.49
     Y
    -0.49
     
    -0.48
     class
    -0.47
     company
    -0.47
     sex
    -0.46
    ixx
    -0.46
    yki
    -0.46
     L
    -0.45
    ]}>
    -0.44
    POSITIVE LOGITS
     Jurí
    0.84
     myſelf
    0.82
     Normdatei
    0.79
    ItemBackground
    0.75
     pleaſure
    0.74
     Theſe
    0.74
    IsMutable
    0.74
     himſelf
    0.73
    těte
    0.73
     purpoſe
    0.73
    Activations Density 0.823%

    No Known Activations