© 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. 3794
    Prev
    Next
    INDEX
    Explanations

    references to maximum and minimum values, particularly in quantitative or measurement contexts

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

    following "max" or "Max"

    np_acts-logits-general · gemini-2.0-flash

    max followed by specific names or limits

    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
     AssemblyCompany
    -0.90
    OGND
    -0.76
    StoreMessageInfo
    -0.73
    tagHelper
    -0.73
    Portale
    -0.64
     {?>
    -0.63
     "',
    -0.61
    ligo
    -0.61
    IUrlHelper
    -0.60
    Rhestr
    -0.59
    POSITIVE LOGITS
    imo
    0.80
     allowable
    0.78
    ium
    0.77
    mum
    0.74
    ima
    0.73
     possible
    0.64
    ims
    0.63
    Allowed
    0.63
    ALLOWED
    0.61
    imas
    0.61
    Activations Density 0.070%

    No Known Activations