© 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. 13713
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to statistical and data recording concepts

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

    Code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    parentheses numbers code

    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
     переписи
    -0.55
    UnknownFieldSet
    -0.54
    coefficients
    -0.51
    IndentedString
    -0.49
    ASKA
    -0.48
    series
    -0.48
     iNdEx
    -0.48
    ༽
    -0.47
    disc
    -0.47
    IsMutable
    -0.46
    POSITIVE LOGITS
    ReusableCell
    0.62
    Diweddarwch
    0.60
     مواليد
    0.57
     magasiner
    0.56
    IsPostBack
    0.56
     cherchés
    0.52
    +#+#
    0.52
    saraba
    0.52
    SizeF
    0.51
    BindingResult
    0.50
    Activations Density 0.102%

    No Known Activations