© 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. 11-GEMMASCOPE-RES-16K
    11. 12621
    Prev
    Next
    INDEX
    Explanations

    technical jargon or abbreviations related to computing or engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -1.35
    AddTagHelper
    -1.16
     AssemblyCulture
    -1.10
     يتيمه
    -1.09
    tagHelperRunner
    -1.07
    featureID
    -1.07
     مرئيه
    -1.05
     tartalomajánló
    -1.04
     Biôgrafia
    -1.04
     '\\;'
    -1.03
    POSITIVE LOGITS
    ↵
    0.53
     
    0.48
    </td>
    0.48
    .
    0.45
    </h3>
    0.45
    ↵↵↵
    0.44
    ↵↵
    0.42
    </h1>
    0.40
     passa
    0.39
    3
    0.38
    Activations Density 0.207%

    No Known Activations