© 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. 3784
    Prev
    Next
    INDEX
    Explanations

    phrases indicating political norms and behaviors, particularly focusing on denial or acceptance of certain truths

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

    Follows words like "for" or "as"

    np_acts-logits-general · gemini-2.0-flash

    taken for granted

    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
     Wikiseite
    -0.67
    Appropriate
    -0.55
     engraçadas
    -0.53
     Appropriate
    -0.51
    calo
    -0.49
    subpackage
    -0.47
     pauvre
    -0.47
    appropriate
    -0.46
     attentive
    -0.45
     רבה
    -0.45
    POSITIVE LOGITS
     guaranteed
    1.03
     unquestion
    1.03
     indisputable
    1.01
     invio
    0.96
     undisputed
    0.95
     certainty
    0.90
     automatic
    0.90
     settled
    0.89
     irreversible
    0.88
     immutable
    0.88
    Activations Density 0.522%

    No Known Activations