© 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. 4395
    Prev
    Next
    INDEX
    Explanations

    quoted speech and expressions of excitement or enthusiasm

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

    Quoted text about positive sentiment

    np_acts-logits-general · gemini-2.0-flash

    positive sentiment statements

    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
    THEN
    -0.59
     dunno
    -0.58
     sometimes
    -0.56
     wondering
    -0.53
    Frage
    -0.53
     question
    -0.52
     GenerationType
    -0.52
     hypothetical
    -0.52
     Frage
    -0.52
    Enllaços
    -0.52
    POSITIVE LOGITS
    Congratulations
    0.77
     Congratulations
    0.76
     delighted
    0.68
     I
    0.63
    nocześnie
    0.63
     thrilled
    0.61
     congratulations
    0.60
    今回の
    0.59
    Together
    0.58
     Excited
    0.58
    Activations Density 0.062%

    No Known Activations