© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 6190
    Prev
    Next
    INDEX
    Explanations

    references to information being easy to obtain or reach

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -1.01
     protoimpl
    -0.91
    MigrationBuilder
    -0.86
    UserScript
    -0.84
    multer
    -0.84
    ########.
    -0.81
    mybatisplus
    -0.80
    dymyr
    -0.76
    Slf
    -0.75
    AndEndTag
    -0.75
    POSITIVE LOGITS
     accessible
    1.47
    accessible
    1.32
     Accessible
    1.27
     accessibility
    1.25
    Accessible
    1.09
     accessibles
    1.06
     accesible
    1.05
     Accessibility
    1.01
    {}'.
    0.98
     inaccessible
    0.95
    Activations Density 0.007%

    No Known Activations