© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 12502
    Prev
    Next
    INDEX
    Explanations

    programming language structure, particularly related to variable assignments and data storage

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

    Code or data snippets

    np_acts-logits-general · gemini-2.0-flash

    Becquelin Cormorant Anecdotes

    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
     Dalton
    -0.83
    AndEndTag
    -0.81
    Dalton
    -0.80
     Cullen
    -0.72
     Salman
    -0.72
     Bajaj
    -0.72
     Fedor
    -0.71
     Wyman
    -0.70
     Mian
    -0.69
     EconPapers
    -0.67
    POSITIVE LOGITS
     Hornet
    0.67
     Paolo
    0.67
     Noe
    0.64
     Qi
    0.64
     Mahoney
    0.63
     ANI
    0.63
     Ott
    0.62
     Poe
    0.62
     Benedict
    0.62
     Dune
    0.61
    Activations Density 0.633%

    No Known Activations