© 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. 16-GEMMASCOPE-RES-16K
    11. 6987
    Prev
    Next
    INDEX
    Explanations

    dialogue exchanges involving conversational cues and emotional reactions

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

    Dialogue punctuation followed by speech markers

    np_acts-logits-general · gemini-2.0-flash

    dialogue attribution verbs

    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
    bootstrapcdn
    -0.83
    SequentialGroup
    -0.68
    jsdelivr
    -0.63
     Normdatei
    -0.58
    ngdoc
    -0.57
    IUrlHelper
    -0.57
    ArgumentParser
    -0.56
    paravant
    -0.54
    MockBean
    -0.54
     الرياضيه
    -0.53
    POSITIVE LOGITS
    脚注の使い方
    0.56
    Personendaten
    0.51
     holding
    0.48
    كويكب
    0.48
    reuung
    0.47
    faf
    0.46
    UnknownFields
    0.46
     jug
    0.45
     assuming
    0.44
     carrying
    0.43
    Activations Density 0.049%

    No Known Activations