© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5455
    Prev
    Next
    INDEX
    Explanations

    phrases associated with scientific studies and their methodologies

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

    Research studies and their purpose

    np_acts-logits-general · gemini-2.0-flash

    investigating effects and relationships

    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
    SequentialGroup
    -0.82
    __(/*!
    -0.69
     médecine
    -0.62
     extérieures
    -0.61
     guste
    -0.58
    škai
    -0.58
     découvertes
    -0.57
    astify
    -0.57
     mauvaises
    -0.56
     prossima
    -0.56
    POSITIVE LOGITS
     relationships
    1.24
     relationship
    1.17
     influence
    1.04
    relationships
    1.02
     effects
    1.01
     impacts
    0.98
     impact
    0.97
    relationship
    0.94
     effect
    0.93
     relations
    0.92
    Activations Density 1.714%

    No Known Activations