© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10401
    Prev
    Next
    INDEX
    Explanations

    programming notations, particularly those related to image handling and structure definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical formulas with vertical lines

    np_acts-logits-general · gemini-2.0-flash

    math or food items like bagels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sjö
    -0.48
    hadap
    -0.48
    клопе
    -0.46
     Lari
    -0.45
     Fonten
    -0.43
     Bradshaw
    -0.42
     Verhält
    -0.41
     Brun
    -0.41
     impresa
    -0.41
    Abp
    -0.41
    POSITIVE LOGITS
    
    3.28
    
    0.94
    
    0.93
     [*]
    0.80
    
    0.69
    ########.
    0.68
    
    0.66
    
    0.60
     CreateTagHelper
    0.59
    
    0.56
    Activations Density 0.049%

    No Known Activations