© 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. 0-GEMMASCOPE-RES-16K
    11. 7224
    Prev
    Next
    INDEX
    Explanations

    phrases indicating dependence or reliance on something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prestige
    -0.35
     prestige
    -0.34
     spice
    -0.34
    Ɓ
    -0.34
     gift
    -0.34
    sstelle
    -0.32
    InputModule
    -0.32
     Outlet
    -0.31
     drin
    -0.31
    </table>
    -0.31
    POSITIVE LOGITS
     relies
    1.31
     rely
    1.30
     depends
    1.24
     depend
    1.23
     relying
    1.20
     Rely
    1.14
     depended
    1.09
    depends
    1.05
    Depend
    1.05
    depend
    1.05
    Activations Density 0.441%

    No Known Activations