© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10160
    Prev
    Next
    INDEX
    Explanations

    terms related to orientation and alignment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Espèce
    -0.61
    EndProject
    -0.57
    AsUp
    -0.57
     ब्रेकडाउन
    -0.55
    Bronnen
    -0.52
    EndGlobalSection
    -0.49
     resourceCulture
    -0.49
    GOTREF
    -0.48
     gyhoeddwyd
    -0.48
    ፩
    -0.47
    POSITIVE LOGITS
     leaning
    0.98
     oriented
    0.83
     orient
    0.79
     inclined
    0.78
    oriented
    0.76
     inclin
    0.76
    leaning
    0.75
     tilted
    0.75
     leaned
    0.73
     Oriented
    0.73
    Activations Density 0.438%

    No Known Activations