© 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. 35-GEMMASCOPE-RES-16K
    11. 7172
    Prev
    Next
    INDEX
    Explanations

    references to video content or multimedia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istung
    -0.30
    立ち
    -0.25
     beach
    -0.25
     strukt
    -0.25
     restaurantes
    -0.25
     لد
    -0.25
    wnątrz
    -0.25
     big
    -0.24
     free
    -0.23
     solid
    -0.23
    POSITIVE LOGITS
    tape
    0.92
    confer
    0.91
     conferencing
    0.88
    tapes
    0.83
    setVerticalGroup
    0.81
    conference
    0.79
    AddTagHelper
    0.75
     noDo
    0.74
     clips
    0.73
     clip
    0.73
    Activations Density 0.086%

    No Known Activations