© 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. 5-GEMMASCOPE-RES-16K
    11. 15440
    Prev
    Next
    INDEX
    Explanations

    references to scientific experiments and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \|_{
    -0.79
     profilo
    -0.77
     Normdatei
    -0.76
     hiér
    -0.74
    paravant
    -0.72
    Continuity
    -0.71
     rédaction
    -0.70
     htons
    -0.68
    وردار
    -0.67
    JKLM
    -0.67
    POSITIVE LOGITS
     experiment
    2.19
     experiments
    2.17
     Experiments
    1.99
     Experiment
    1.97
    Experiments
    1.84
    Experiment
    1.82
     experimental
    1.81
     EXPERIMENT
    1.80
     experimentation
    1.77
    experiment
    1.76
    Activations Density 0.095%

    No Known Activations