© 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. 7-GEMMASCOPE-RES-16K
    11. 13504
    Prev
    Next
    INDEX
    Explanations

    references to various types of adapters in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <u>
    -0.36
    her
    -0.36
    nh
    -0.35
                                   
    -0.35
      
    -0.35
     Hill
    -0.34
    "
    -0.33
     
    -0.33
    Hill
    -0.33
    실
    -0.33
    POSITIVE LOGITS
    Adapter
    3.19
     adapter
    2.83
    adapter
    2.83
     Adapter
    2.78
     adapters
    2.55
    adapters
    2.28
    Adapters
    2.22
     Adap
    2.20
     adaptor
    2.08
     adapt
    1.98
    Activations Density 0.075%

    No Known Activations