© 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. 15373
    Prev
    Next
    INDEX
    Explanations

    legal mandates or requirements stated in contractual or legislative language

    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
     poffible
    -0.95
     raiſ
    -0.94
     Efq
    -0.90
     Diſ
    -0.90
     Reſ
    -0.90
     Chriftian
    -0.90
     houſe
    -0.86
     diſt
    -0.83
     myſelf
    -0.82
     fince
    -0.82
    POSITIVE LOGITS
     shall
    2.00
    shall
    1.76
     SHALL
    1.67
     Shall
    1.54
    Shall
    1.49
     shalt
    1.04
    hereinafter
    0.90
    LookAnd
    0.87
    gebühr
    0.81
    haltet
    0.79
    Activations Density 0.092%

    No Known Activations