© 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. 24-GEMMASCOPE-RES-16K
    11. 4962
    Prev
    Next
    INDEX
    Explanations

    phrases that describe types or kinds of things

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

    "kind/type of"

    np_acts-logits-general · gemini-2.0-flash

    types and kinds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.69
    fjspx
    -0.67
    Билгалдахарш
    -0.67
    featureID
    -0.64
     autorytatywna
    -0.64
     محفوظة
    -0.63
     volontà
    -0.62
    EDEFAULT
    -0.61
    ThroughAttribute
    -0.61
    Източници
    -0.61
    POSITIVE LOGITS
     thing
    0.67
     scenario
    0.66
     interaction
    0.64
     creature
    0.59
     деятельности
    0.59
     activity
    0.59
     nourishment
    0.58
     situation
    0.58
     arrangement
    0.58
     clientele
    0.57
    Activations Density 0.143%

    No Known Activations