Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2486
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "default" in various contexts

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

    Default values or default implementations

    np_acts-logits-general · gemini-2.0-flash

    default configuration values

    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
    OGND
    -0.81
    وانید
    -0.63
     initComponents
    -0.59
    مصادر
    -0.56
    Aholisi
    -0.54
    Rohy
    -0.53
    ViewChild
    -0.53
    eraard
    -0.51
    ukah
    -0.51
     jadx
    -0.51
    POSITIVE LOGITS
    CloseOperation
    0.99
    情况下
    0.75
    RenderAtEndOf
    0.65
    값
    0.63
    ing
    0.61
     values
    0.58
    值
    0.58
     solitaire
    0.57
     rudder
    0.53
     Photocase
    0.52
    Activations Density 0.057%

    No Known Activations