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. 12776
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terminologies related to processes and measurements

    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
     دائ
    -0.65
     snippetHide
    -0.52
    styleType
    -0.51
    Espèce
    -0.51
     permanently
    -0.50
     Italijani
    -0.50
    XtraReports
    -0.49
     autorytatywna
    -0.49
    crombie
    -0.48
    országban
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    0.67
    AddTagHelper
    0.66
     successive
    0.64
     subsequent
    0.63
     trials
    0.60
     iterations
    0.59
     several
    0.59
    several
    0.58
     cycles
    0.57
     mehrm
    0.56
    Activations Density 0.365%

    No Known Activations