© 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. 5072
    Prev
    Next
    INDEX
    Explanations

    discussions about unnecessary or redundant actions and concepts

    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
     Heraus
    -0.54
    zional
    -0.54
     Wicidata
    -0.53
    eph
    -0.53
    ième
    -0.51
    mavi
    -0.51
    ähr
    -0.50
     Νο
    -0.50
    gman
    -0.50
     Violations
    -0.50
    POSITIVE LOGITS
     unnecessary
    1.15
     pointless
    1.14
     useless
    1.05
     needlessly
    1.04
     inneces
    1.00
     unnecessarily
    1.00
     needless
    1.00
     wasting
    0.99
     inutile
    0.98
     waste
    0.97
    Activations Density 0.320%

    No Known Activations