© 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. 23-GEMMASCOPE-RES-16K
    11. 15224
    Prev
    Next
    INDEX
    Explanations

    complex relationships and interactions, often involving emotions and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ományos
    -0.42
    etro
    -0.41
     profess
    -0.41
    importe
    -0.40
    نين
    -0.39
    UTE
    -0.39
     relativo
    -0.39
    eral
    -0.38
    isinstance
    -0.38
    engo
    -0.38
    POSITIVE LOGITS
     pinulongan
    0.89
     تضيفلها
    0.88
    setVerticalGroup
    0.85
    ConstraintMaker
    0.83
    OGND
    0.80
    
    0.75
    Personensuche
    0.75
    انجليز
    0.75
     الرياضيه
    0.73
    Personendaten
    0.72
    Activations Density 0.079%

    No Known Activations