© 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. 12113
    Prev
    Next
    INDEX
    Explanations

    phrases related to assessments or evaluations of situations or conditions

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

    that often begin a sentence or clause

    np_acts-logits-general · gemini-2.0-flash

    Hence, suggestions, requirements, or conditions

    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
     ERS
    -0.29
    batis
    -0.29
     absl
    -0.28
     suns
    -0.26
     wort
    -0.25
    !")
    -0.25
     AEC
    -0.25
     KT
    -0.24
     EGL
    -0.24
     horned
    -0.24
    POSITIVE LOGITS
    sizeCache
    0.93
    OGND
    0.88
     تضيفلها
    0.87
    tidaknya
    0.86
    expandindo
    0.86
    tvguidetime
    0.85
     quæ
    0.84
     hunne
    0.83
    those
    0.82
     zijne
    0.82
    Activations Density 1.199%

    No Known Activations