© 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. 14966
    Prev
    Next
    INDEX
    Explanations

    descriptions of complexity and technology-related attributes, particularly in a cultural or social context

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

    Adjective followed by comma/period/and

    np_acts-logits-general · gemini-2.0-flash

    descriptive words

    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
     betweenstory
    -0.70
    dighet
    -0.66
    GEBURTSDATUM
    -0.66
    yntaxException
    -0.66
    锈钢
    -0.65
    Демографія
    -0.64
    ]){
    -0.63
    sbericht
    -0.62
    parency
    -0.62
    AndEndTag
    -0.61
    POSITIVE LOGITS
     enough
    1.53
    enough
    1.01
     demais
    0.96
     genug
    0.94
     ENOUGH
    0.91
     genoeg
    0.90
     compared
    0.84
     Enough
    0.84
     yet
    0.80
    Enough
    0.80
    Activations Density 0.707%

    No Known Activations