© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8373
    Prev
    Next
    INDEX
    Explanations

    terms related to specific scientific concepts and measurements

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

    ending in a suffix

    np_acts-logits-general · gemini-2.0-flash

    photonic, inflammatory, phosphoryl

    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
    able
    -1.57
    ability
    -1.20
    age
    -1.15
    ages
    -1.03
    ably
    -1.00
    au
    -0.96
    ables
    -0.93
    ain
    -0.93
    ak
    -0.92
    ag
    -0.91
    POSITIVE LOGITS
    tvguidetime
    0.58
    er
    0.48
     [*]
    0.47
     Hyperion
    0.43
    genheim
    0.42
    alism
    0.42
    ism
    0.41
     referrerpolicy
    0.41
    ER
    0.41
     betweenstory
    0.41
    Activations Density 0.605%

    No Known Activations