© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9032
    Prev
    Next
    INDEX
    Explanations

    references to various types of evaluations or conclusions related to justice or court decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laston
    -0.34
    ürn
    -0.33
    verket
    -0.33
     pilot
    -0.33
    UseVisualStyle
    -0.32
     explosion
    -0.32
     spä
    -0.32
    AutoScaleMode
    -0.31
    acán
    -0.30
    redhat
    -0.30
    POSITIVE LOGITS
     including
    1.23
    including
    1.10
     Including
    1.03
    Including
    1.03
     notamment
    0.99
    包括
    0.96
     antaranya
    0.95
     включая
    0.94
    Например
    0.90
     notably
    0.90
    Activations Density 0.760%

    No Known Activations