© 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. 20-GEMMASCOPE-RES-16K
    11. 6706
    Prev
    Next
    INDEX
    Explanations

    keywords and symbols related to programming logic and conditions

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

    Conditions for exiting/stopping a loop

    np_acts-logits-general · gemini-2.0-flash

    loop termination condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     CURIAM
    -0.57
    MLLoader
    -0.54
    extAlignment
    -0.52
    ፩
    -0.49
     AssemblyCompany
    -0.49
    majánló
    -0.48
    Carry
    -0.48
     protoimpl
    -0.47
    +#+#
    -0.47
    Tikang
    -0.46
    POSITIVE LOGITS
    CloseOperation
    0.47
     stops
    0.35
     irgendwann
    0.35
     ended
    0.33
     terminated
    0.31
    WaitGroup
    0.31
     terminates
    0.31
    MessageTagHelper
    0.30
     eventually
    0.30
    harapkan
    0.30
    Activations Density 0.238%

    No Known Activations