© 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. 3-GEMMASCOPE-RES-16K
    11. 5837
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions indicating examples and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorisations
    -0.56
    DockStyle
    -0.51
     jsPsych
    -0.51
    migrationBuilder
    -0.47
    MessageTagHelper
    -0.44
    ptid
    -0.42
    ACHUSET
    -0.41
    funeral
    -0.41
    antart
    -0.40
     AssemblyVersion
    -0.40
    POSITIVE LOGITS
     including
    1.19
     Including
    1.05
     esimerkiksi
    1.03
    包括
    1.03
    Including
    1.02
     például
    1.01
     notamment
    0.98
    例えば
    0.96
     například
    0.95
    including
    0.95
    Activations Density 0.316%

    No Known Activations