© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5294
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with parenthesis and brackets

    np_acts-logits-general · gemini-2.0-flash

    code blocks and html tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.92
    IntoConstraints
    -0.78
     '{@
    -0.77
    Personendaten
    -0.75
    ngdoc
    -0.73
    SequentialGroup
    -0.72
    PerformLayout
    -0.70
     transfieras
    -0.69
    sidemargin
    -0.67
    GTCX
    -0.66
    POSITIVE LOGITS
    ↵↵
    1.21
    ↵↵↵
    0.40
    </blockquote>
    0.37
    ↵↵↵↵
    0.35
    　　
    0.33
     Abonnez
    0.31
    </h3>
    0.29
    </h2>
    0.29
     yani
    0.29
    cjon
    0.29
    Activations Density 0.363%

    No Known Activations