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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15794
    Prev
    Next
    INDEX
    Explanations

    references to arguments and their validation 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 @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithMany
    -0.55
    ="#"><
    -0.51
     CreateTagHelper
    -0.50
    Portail
    -0.49
    :");
    
    -0.49
    weightedMode
    -0.48
     gyhoeddwyd
    -0.48
     $:$
    -0.48
    }{|
    -0.47
    ***********/
    -0.46
    POSITIVE LOGITS
    Argument
    1.05
     argument
    1.03
    argument
    0.97
     arguments
    0.96
     Argument
    0.95
    Args
    0.92
     Arguments
    0.91
     args
    0.88
    args
    0.88
    arguments
    0.87
    Activations Density 0.084%

    No Known Activations