© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8971
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to political criticism and accountability

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

    doubt or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    allegedly, supposedly, questionable claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.51
     oldukça
    -0.45
     consape
    -0.43
     hué
    -0.43
    Argu
    -0.42
    nement
    -0.40
     IMHO
    -0.39
     IMO
    -0.39
     dürfte
    -0.39
    fikasi
    -0.39
    POSITIVE LOGITS
     somehow
    1.02
     supposedly
    0.93
     яко
    0.91
     angeb
    0.71
     allegedly
    0.69
     supuestamente
    0.69
     magically
    0.67
     Somehow
    0.64
     supposed
    0.63
     purported
    0.63
    Activations Density 1.044%

    No Known Activations