© 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. 33-GEMMASCOPE-RES-16K
    11. 6153
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features related to reclining chairs and their mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.49
    MENAFN
    -0.49
    nader
    -0.48
    Robots
    -0.47
     StringTokenizer
    -0.46
     tani
    -0.46
    robot
    -0.45
     REFR
    -0.44
     Robots
    -0.43
    locu
    -0.43
    POSITIVE LOGITS
     adjustable
    0.56
     casters
    0.54
     braços
    0.51
     réglable
    0.50
    Adjustable
    0.50
     backrest
    0.49
     seat
    0.49
     arms
    0.49
    把手
    0.48
     handles
    0.47
    Activations Density 0.297%

    No Known Activations