© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 10577
    Prev
    Next
    INDEX
    Explanations

    references to academic journal publications and their details

    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
    Unmanaged
    -0.33
     urma
    -0.33
    GTCX
    -0.31
    +#+
    -0.30
     timpul
    -0.30
    estinal
    -0.30
    dflare
    -0.30
     Roskov
    -0.30
    caped
    -0.29
    poken
    -0.29
    POSITIVE LOGITS
     IEEE
    0.82
    IEEE
    0.70
     насељу
    0.68
     CreateTagHelper
    0.60
    chartInstance
    0.57
     ieee
    0.57
    ieee
    0.56
    ziasztok
    0.52
     useAppContext
    0.51
    PreferredItem
    0.49
    Activations Density 0.345%

    No Known Activations