© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14124
    Prev
    Next
    INDEX
    Explanations

    symbols and operators commonly used in programming and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.68
    MigrationBuilder
    -0.52
     fotográfica
    -0.45
    alyptus
    -0.44
    OrWhiteSpace
    -0.44
     Photocase
    -0.43
     táctil
    -0.43
     Vikipedi
    -0.43
     anún
    -0.42
    Портали
    -0.41
    POSITIVE LOGITS
    是没有
    0.48
    是有
    0.48
    construct
    0.46
    ONY
    0.45
    是在
    0.45
    是被
    0.44
    是可以
    0.43
    都是在
    0.43
    是想
    0.43
     Quintana
    0.42
    Activations Density 0.197%

    No Known Activations