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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8441
    Prev
    Next
    INDEX
    Explanations

    elements that highlight political polarization and its effects

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

    demonstration or proof

    np_acts-logits-general · gemini-2.0-flash

    demonstrates or shows something

    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
     ISNI
    -0.69
    المكان
    -0.60
    fjspx
    -0.59
     >=",
    -0.58
     كومونز
    -0.58
    djangoproject
    -0.56
     mergeFrom
    -0.54
    ագրություններ
    -0.53
     previsão
    -0.53
     casquette
    -0.52
    POSITIVE LOGITS
     demonstrates
    1.89
     demonstrating
    1.88
     demonstrate
    1.85
     proves
    1.73
     proof
    1.64
     demostrar
    1.63
     demonstrated
    1.62
     demonstration
    1.61
     proving
    1.61
     prove
    1.61
    Activations Density 0.379%

    No Known Activations