© 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. 16-GEMMASCOPE-RES-16K
    11. 4930
    Prev
    Next
    INDEX
    Explanations

    instances of emotional expression or inner dialogue

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

    Follows periods in dialogue or text

    np_acts-logits-general · gemini-2.0-flash

    code or mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stället
    -0.57
     économies
    -0.56
     paſſ
    -0.52
    CppMethod
    -0.52
     enfans
    -0.51
     ſhe
    -0.51
     ſur
    -0.50
    forRoot
    -0.50
    ]=>
    -0.50
     ſch
    -0.50
    POSITIVE LOGITS
     swears
    0.68
     ©️
    0.64
    Personendaten
    0.62
     shoved
    0.61
     colouring
    0.59
     swore
    0.57
    دانشنامهٔ
    0.56
    oOo
    0.56
     tumblr
    0.55
     Tumblr
    0.55
    Activations Density 0.222%

    No Known Activations