© 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. 7488
    Prev
    Next
    INDEX
    Explanations

    information related to cognitive impairments and disorders

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

    "...with impaired [cognitive ability/memory/etc.]"

    np_acts-logits-general · gemini-2.0-flash

    impaired cognitive and spatial performance

    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
    ValueStyle
    -0.58
     Relief
    -0.51
     Alar
    -0.49
     Garanti
    -0.47
     relief
    -0.46
    heating
    -0.45
     interna
    -0.45
     rato
    -0.44
     biotechnology
    -0.44
     sleeves
    -0.44
    POSITIVE LOGITS
     memory
    0.92
    memory
    0.82
     cognitive
    0.77
     Memory
    0.77
     spatial
    0.75
    Memory
    0.75
     mémoire
    0.75
     dexterity
    0.73
     MEMORY
    0.72
     motor
    0.72
    Activations Density 0.513%

    No Known Activations