Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14114
    Prev
    Next
    INDEX
    Explanations

    references to the abbreviation "em" and its variations, indicating its strong association with the term

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

    Tokens starting with "em", often "em "

    np_acts-logits-general · gemini-2.0-flash

    words starting with em

    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
    CodeAttribute
    -0.64
    BagLayout
    -0.61
    jupiter
    -0.60
    ateral
    -0.56
    RUnlock
    -0.55
    JpaRepository
    -0.53
    SIDE
    -0.51
    fiore
    -0.51
     newState
    -0.51
    postolic
    -0.50
    POSITIVE LOGITS
     Emb
    0.56
    NewUrlParser
    0.55
    +#+#
    0.55
    ulating
    0.55
    ulate
    0.53
     Em
    0.53
     pire
    0.53
    NameInMap
    0.51
    ulates
    0.51
    +#+
    0.49
    Activations Density 0.133%

    No Known Activations