© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 9796
    Prev
    Next
    INDEX
    Explanations

    connections and similarities between various concepts and contexts, particularly in relation to crimes or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodeAttribute
    -0.48
    ECTO
    -0.43
    defineProperty
    -0.43
     استنادى
    -0.42
    éos
    -0.41
     miệng
    -0.41
    #!/
    -0.41
     StringVar
    -0.41
     mAdapter
    -0.40
    ments
    -0.40
    POSITIVE LOGITS
     similarities
    1.35
     similarity
    1.31
     similar
    1.23
     SIMILAR
    1.17
     alike
    1.13
    similar
    1.11
    Similar
    1.09
     Similar
    1.06
     Similarity
    1.05
     ähnlichen
    1.04
    Activations Density 0.473%

    No Known Activations