© 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. 4044
    Prev
    Next
    INDEX
    Explanations

    phrases related to options, permissions, and flexibility

    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
    LabelTagHelper
    -0.61
    要
    -0.43
    сным
    -0.41
    InputTagHelper
    -0.39
     trang
    -0.38
    ain
    -0.38
    Nueva
    -0.38
     indispens
    -0.37
    ちょ
    -0.37
     ran
    -0.37
    POSITIVE LOGITS
     dowol
    1.01
     librement
    0.97
     whome
    0.91
    ConstraintMaker
    0.89
    IntoConstraints
    0.88
    AndEndTag
    0.87
     whatever
    0.87
     belieb
    0.86
     anytime
    0.86
     whatsoever
    0.83
    Activations Density 0.243%

    No Known Activations