© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15276
    Prev
    Next
    INDEX
    Explanations

    mentions of political entities and claims concerning their actions or responsibilities

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

    Hypothetical scenarios and conditional statements

    np_acts-logits-general · gemini-2.0-flash

    if it were

    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
     may
    -1.11
     probably
    -1.11
    may
    -1.06
    probably
    -1.04
    Probably
    -0.95
     Probably
    -0.92
     mungkin
    -0.87
     might
    -0.82
     prolly
    -0.82
     شاید
    -0.81
    POSITIVE LOGITS
     were
    0.92
     ever
    0.90
     weren
    0.89
     hadn
    0.84
    Were
    0.80
     fossero
    0.80
     fueran
    0.79
     avesse
    0.79
     fizer
    0.78
    Personendaten
    0.77
    Activations Density 0.556%

    No Known Activations