© 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. 7447
    Prev
    Next
    INDEX
    Explanations

    issues related to scarcity and lack of resources or support in various contexts

    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
     salute
    -0.38
     aventures
    -0.35
    schmidt
    -0.33
    NullCheck
    -0.31
    GroupLayout
    -0.31
    nextProps
    -0.31
    Topping
    -0.29
    Takeaways
    -0.29
     Arbeiten
    -0.29
    _));
    -0.29
    POSITIVE LOGITS
     infrastructure
    1.25
     resources
    1.12
    infrastructure
    1.09
     infraestructura
    1.05
     infrastructures
    1.05
     infrastruktur
    1.01
    frastructure
    1.00
     expertise
    0.98
     manpower
    0.97
     tools
    0.87
    Activations Density 0.787%

    No Known Activations