© 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. 20-GEMMASCOPE-RES-16K
    6. 8660
    Prev
    Next
    INDEX
    Explanations

    URLs and links to web content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -1.05
    __":
    
    -0.90
     $_(
    -0.89
     queſta
    -0.89
     ſch
    -0.79
    出版年
    -0.75
     CURIAM
    -0.73
     ſind
    -0.73
    __':
    
    -0.73
    ✨:
    -0.72
    POSITIVE LOGITS
    https
    0.56
    http
    0.56
     https
    0.46
    ↵↵
    0.45
     http
    0.43
     disebutkan
    0.40
    #
    0.40
    I
    0.40
    ,
    0.40
     mencionado
    0.39
    Activations Density 0.524%

    No Known Activations