© 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. 4-GEMMASCOPE-RES-16K
    11. 1273
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal actions or the commitment of crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Xaml
    -0.71
    posedge
    -0.64
    +#+#
    -0.62
     continúas
    -0.61
    AccessorTable
    -0.61
     Orrell
    -0.59
    Xna
    -0.59
    abstractmethod
    -0.57
    yw
    -0.56
    fjspx
    -0.56
    POSITIVE LOGITS
     commit
    1.32
     committing
    1.30
     Commit
    1.23
     commits
    1.18
    commit
    1.17
     committed
    1.11
     Committed
    1.06
    Commit
    1.05
     COMMIT
    1.02
    committed
    0.98
    Activations Density 0.193%

    No Known Activations