© 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. 16-GEMMASCOPE-RES-16K
    11. 4363
    Prev
    Next
    INDEX
    Explanations

    tokens and values related to statistics and data representation

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

    Numbers followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    2 or 3 laps

    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
     PartialEq
    -0.66
     Accesat
    -0.66
    zeptember
    -0.65
     OkHttpClient
    -0.64
    VStack
    -0.63
     positive
    -0.60
    CppCodeGen
    -0.59
     Ανακτήθηκε
    -0.59
     EnglishChoose
    -0.58
     FormsModule
    -0.58
    POSITIVE LOGITS
     betweenstory
    0.70
    Unnamed
    0.53
     untitled
    0.53
     denominada
    0.51
     تانيه
    0.51
    lichkeiten
    0.50
     modernize
    0.49
    Jeografia
    0.49
    IUrlHelper
    0.48
    untitled
    0.48
    Activations Density 0.186%

    No Known Activations