© 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. 3830
    Prev
    Next
    INDEX
    Explanations

    phrases related to recognition and commendation in a formal context

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

    Follows punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    reporting speech or adding information

    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
    ביוגרפיה
    -0.62
    tidaknya
    -0.61
    AddHtmlAttribute
    -0.57
    delwed
    -0.57
     محفوظة
    -0.54
     виправивши
    -0.53
     חיצוניים
    -0.53
    ensed
    -0.53
     Infórmanos
    -0.52
     tombé
    -0.51
    POSITIVE LOGITS
    他說
    0.69
    他说
    0.69
    وأضاف
    0.65
     Referring
    0.65
    ANTLR
    0.64
    她说
    0.60
    Referring
    0.60
     उन्होंने
    0.59
    homonymie
    0.58
     saying
    0.57
    Activations Density 0.220%

    No Known Activations