© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12665
    Prev
    Next
    INDEX
    Explanations

    structures that summarize or conclude discussions or studies

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

    tables or figures

    np_acts-logits-general · gemini-2.0-flash

    numbers and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.26
     tartalomajánló
    -1.18
     Theſe
    -1.07
    AddTagHelper
    -1.05
     myſelf
    -1.03
     Monfieur
    -1.03
     ་་
    -1.01
     ―――――
    -1.00
     contextLoads
    -1.00
    rungsseite
    -0.99
    POSITIVE LOGITS
     
    0.81
    1
    0.74
    2
    0.68
    .
    0.66
    0
    0.66
    3
    0.62
    9
    0.61
    5
    0.61
      
    0.61
    6
    0.60
    Activations Density 0.141%

    No Known Activations