© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-GEMMASCOPE-RES-16K
    11. 1121
    Prev
    Next
    INDEX
    Explanations

    discussions around technology and software usability

    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
    <strong>
    -0.56
     
    -0.55
    ’;
    -0.54
     אשר
    -0.54
    . 
    -0.54
    </h2>
    -0.52
    ることができる
    -0.50
     –,
    -0.50
    することができます
    -0.50
    ’,
    -0.49
    POSITIVE LOGITS
     IIRC
    1.15
     iirc
    1.03
     IMHO
    1.02
     stuff
    1.01
    FWIW
    0.96
     prolly
    0.95
     dunno
    0.93
    YMMV
    0.92
    +#+#
    0.91
    IMHO
    0.91
    Activations Density 1.913%

    No Known Activations