© 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 EvalsExportsAPI 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. 7112
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to angles and their measurements

    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
     Cuth
    -0.92
     ſtate
    -0.82
     pleaſure
    -0.82
     purpoſe
    -0.81
     McCulloch
    -0.78
     Monfieur
    -0.76
     deſt
    -0.76
    __(/*!
    -0.75
     doInBackground
    -0.75
    >−
    -0.75
    POSITIVE LOGITS
     angle
    2.42
     angles
    2.34
     Angle
    2.26
    Angle
    2.07
     ANGLE
    2.04
     Angles
    2.01
    angle
    1.91
    Angles
    1.82
    angles
    1.69
    ANGLE
    1.65
    Activations Density 0.048%

    No Known Activations