© 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. 18-GEMMASCOPE-RES-16K
    11. 2177
    Prev
    Next
    INDEX
    Explanations

    themes related to political discourse and revolutionary ideology

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

    nations, revolution, or patriotic sentiment

    np_acts-logits-general · gemini-2.0-flash

    revolutionary line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initially
    -0.53
     usually
    -0.52
     pretty
    -0.51
     maybe
    -0.50
     oddly
    -0.50
     provavelmente
    -0.49
     possibly
    -0.49
     mostly
    -0.49
     eset
    -0.49
    usually
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.84
     nation
    0.82
     المعيارى
    0.80
    zzleHttp
    0.79
     '\\;'
    0.78
    LEncoder
    0.77
    NUMX
    0.76
    ArgsConstructor
    0.75
     patriotic
    0.75
    tvguidetime
    0.73
    Activations Density 0.214%

    No Known Activations