© 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. 12337
    Prev
    Next
    INDEX
    Explanations

    references to the concept of carrying out actions or responsibilities

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

    "carried" or "carry"

    np_acts-logits-general · gemini-2.0-flash

    carry out actions

    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
    XmlAccessType
    -0.66
    ukone
    -0.66
    tanleria
    -0.58
     fallu
    -0.57
    PhysRev
    -0.57
    částí
    -0.57
    ficamente
    -0.57
    NOPQRST
    -0.56
    enterOuterAlt
    -0.55
     pinulongan
    -0.55
    POSITIVE LOGITS
     carried
    0.99
     carry
    0.98
    carry
    0.91
    forward
    0.90
     forward
    0.90
    carried
    0.88
     Carry
    0.87
    Carry
    0.86
     carries
    0.86
     CARRY
    0.82
    Activations Density 0.075%

    No Known Activations