© 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. 15139
    Prev
    Next
    INDEX
    Explanations

    terms related to birth and childbirth

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

    "Birth" tokens followed usually by "of"

    np_acts-logits-general · gemini-2.0-flash

    birth control or certificates

    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
    ネル
    -0.49
     zařízení
    -0.48
    ு
    -0.48
    lucene
    -0.45
    Quanto
    -0.44
     fråga
    -0.44
    儡
    -0.44
    vanna
    -0.44
     berbahaya
    -0.44
     noix
    -0.43
    POSITIVE LOGITS
     EnglishChoose
    0.74
     ModelExpression
    0.71
    SequentialGroup
    0.68
    ंदीखरीदारी
    0.68
    WireFormatLite
    0.67
     pangs
    0.66
     centenary
    0.65
    èdia
    0.65
     month
    0.64
    tvguidetime
    0.64
    Activations Density 0.108%

    No Known Activations