© 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. 4738
    Prev
    Next
    INDEX
    Explanations

    references to actions involving starting, setting up, or accessing accounts and resources online

    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
     pleaſure
    -0.78
     purpoſe
    -0.71
     uſ
    -0.71
     deſt
    -0.68
     juſt
    -0.68
     ſta
    -0.66
     ſtate
    -0.66
     faſt
    -0.66
     raiſ
    -0.65
     Jefus
    -0.64
    POSITIVE LOGITS
     AttributeSet
    0.70
    ISupport
    0.65
    árol
    0.53
     owning
    0.51
    AttributeSet
    0.49
     básicas
    0.47
     membership
    0.46
    一台
    0.46
    ghen
    0.45
     собі
    0.45
    Activations Density 0.199%

    No Known Activations