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. 15-GEMMASCOPE-RES-16K
    6. 1805
    Prev
    Next
    INDEX
    Explanations

    terms related to materials, specifically in relation to cooling, coatings, and structural engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.71
    #+#
    -0.61
    Viitteet
    -0.60
    tagHelperRunner
    -0.60
    Viited
    -0.58
     pinulongan
    -0.57
    AndEndTag
    -0.57
     يتيمه
    -0.56
    angliski
    -0.56
    kehren
    -0.53
    POSITIVE LOGITS
     ReactDOM
    0.55
     preparations
    0.54
     prépar
    0.51
     подготов
    0.51
    JsonHelper
    0.49
     Preparations
    0.49
    afficheront
    0.48
    expandindo
    0.48
     preexisting
    0.48
    UnusedPrivate
    0.48
    Activations Density 0.960%

    No Known Activations