© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6894
    Prev
    Next
    INDEX
    Explanations

    elements related to lists and data structures in programming

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

    Programming code and database operations

    np_acts-logits-general · gemini-2.0-flash

    list of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .}\
    -0.64
    googleapis
    -0.64
    bufio
    -0.62
    GHIJKLM
    -0.62
    ѝ
    -0.61
     Mail
    -0.59
     _)
    -0.59
    ")==
    -0.58
    ureka
    -0.57
    ]='\
    -0.57
    POSITIVE LOGITS
    Personendaten
    0.62
     judiciales
    0.61
     bezeichneter
    0.58
     disponibilités
    0.58
     amables
    0.56
    +#+#
    0.54
     neutre
    0.54
    numerusform
    0.53
    包括
    0.52
    Scénario
    0.52
    Activations Density 0.141%

    No Known Activations