© 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. 24-GEMMASCOPE-RES-16K
    11. 14801
    Prev
    Next
    INDEX
    Explanations

    terms related to family planning and discussions surrounding it

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

    followed by prepositions or verbs

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs followed by prepositions or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.75
     beginnetje
    -0.61
    Datuak
    -0.58
    ®
    -0.53
     nachos
    -0.50
     ComVisible
    -0.49
     validamos
    -0.49
     gotta
    -0.48
     AWESOME
    -0.47
     aceptas
    -0.46
    POSITIVE LOGITS
     provincial
    0.72
     nationalist
    0.70
     reportedly
    0.69
     locals
    0.67
     bureaucratic
    0.66
     NGOs
    0.65
     villagers
    0.63
     unregistered
    0.62
     denunci
    0.62
     nationalists
    0.62
    Activations Density 0.625%

    No Known Activations