© 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. 14986
    Prev
    Next
    INDEX
    Explanations

    arguments questioning decisions or actions

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

    Follows, colons, and other punctuation

    np_acts-logits-general · gemini-2.0-flash

    explaining as follows

    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
     صوتيه
    -0.84
    Portail
    -0.83
     otomatig
    -0.82
     nahilalakip
    -0.74
    PreferredItem
    -0.74
    ThroughAttribute
    -0.68
    expandindo
    -0.68
     Administrativna
    -0.68
    tagHelperRunner
    -0.65
     للمعارف
    -0.65
    POSITIVE LOGITS
    是这样的
    0.72
     Suppose
    0.71
    Suppose
    0.66
     Basically
    0.65
    Basically
    0.64
     Essentially
    0.62
     folgendes
    0.61
     imagine
    0.61
     Imagine
    0.59
     suppose
    0.58
    Activations Density 0.343%

    No Known Activations