© 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. 2-GEMMASCOPE-RES-16K
    11. 1011
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.58
    avimas
    -0.47
    avimo
    -0.41
     rather
    -0.40
    établir
    -0.39
     dře
    -0.39
    ēju
    -0.39
     τὴν
    -0.39
     avrebbero
    -0.38
     disposiciones
    -0.37
    POSITIVE LOGITS
    IntoConstraints
    0.93
    endphp
    0.86
    
    0.85
    GEBURTSDATUM
    0.85
    olerance
    0.81
    IUrlHelper
    0.81
     unmute
    0.79
    fjspx
    0.79
    StoryboardSegue
    0.79
     AssemblyTitle
    0.78
    Activations Density 4.848%

    No Known Activations