© 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. 24-GEMMASCOPE-RES-16K
    11. 4779
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting code used in technical documents

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

    Starts a new item in a list

    np_acts-logits-general · gemini-2.0-flash

    list item commands

    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
    禁
    -0.59
     vet
    -0.56
    ljeno
    -0.53
    processable
    -0.51
    yfikacja
    -0.50
     Connectez
    -0.48
    oner
    -0.47
    dried
    -0.47
     Soriano
    -0.46
    niosek
    -0.46
    POSITIVE LOGITS
    begin
    1.01
    section
    0.91
    texttt
    0.76
     kasarigan
    0.75
    textbackslash
    0.66
    subsubsection
    0.63
    href
    0.60
     وتسجيلات
    0.60
    subsection
    0.59
     OMITBAD
    0.59
    Activations Density 0.013%

    No Known Activations