© 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. 34-GEMMASCOPE-RES-16K
    11. 13112
    Prev
    Next
    INDEX
    Explanations

    technical terms related to travel and transportation details, including pricing and destination information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     roll
    -0.36
     dil
    -0.35
     Roll
    -0.33
     rolls
    -0.33
     rolled
    -0.32
    dil
    -0.32
     Shi
    -0.31
     ROLL
    -0.31
     Cap
    -0.31
     Kie
    -0.30
    POSITIVE LOGITS
     round
    1.58
    Round
    1.41
    round
    1.39
     Round
    1.33
     ROUND
    1.27
    ROUND
    1.19
     redondo
    0.98
     andata
    0.97
     redonda
    0.90
    trip
    0.89
    Activations Density 0.297%

    No Known Activations