© 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. 13678
    Prev
    Next
    INDEX
    Explanations

    phrases expressing measurement or comparison

    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
    BeginContext
    -0.49
    Schedulers
    -0.42
    stdc
    -0.39
    Билгалдахарш
    -0.37
    uxxxx
    -0.35
    ioutil
    -0.34
    trägen
    -0.34
    SpringRunner
    -0.33
    ponses
    -0.33
     SearchView
    -0.33
    POSITIVE LOGITS
     much
    1.90
    much
    1.62
    Much
    1.47
     Much
    1.35
     MUCH
    1.20
     far
    1.08
     palju
    1.04
     paljon
    1.01
    viel
    1.00
     mucho
    0.95
    Activations Density 0.503%

    No Known Activations