© 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. 3191
    Prev
    Next
    INDEX
    Explanations

    constructs related to object-oriented programming, particularly class and method declarations

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

    Follows specific keywords such as "final", "(", ","

    np_acts-logits-general · gemini-2.0-flash

    Java method signatures

    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
      
    -0.57
     od
    -0.55
     as
    -0.54
    ↵↵↵
    -0.50
     
    -0.50
     (
    -0.49
    <strong>
    -0.47
    ↵↵
    -0.47
     /
    -0.46
     in
    -0.46
    POSITIVE LOGITS
    Datuak
    1.14
    دانشنامهٔ
    1.14
    boolean
    1.02
    rungsseite
    1.00
     boolean
    0.99
    :✨
    0.98
     يتيمه
    0.98
    ^(@)
    0.97
    AddTagHelper
    0.97
     ―――――
    0.94
    Activations Density 0.161%

    No Known Activations