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. 1-GEMMASCOPE-RES-16K
    6. 14811
    Prev
    Next
    INDEX
    Explanations

    references to specific technical objects and concepts, particularly within coding and scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.54
    MessageOf
    -0.53
    ToolStripButton
    -0.50
     وصلة
    -0.50
    μφωνα
    -0.49
    bigsqcup
    -0.48
     sû
    -0.47
     Prefeitura
    -0.47
    intenant
    -0.47
    orsche
    -0.47
    POSITIVE LOGITS
     pinulongan
    0.74
    ILayout
    0.72
     twin
    0.71
    IsPostBack
    0.68
     EventArgs
    0.67
    Portály
    0.67
    enumi
    0.65
    makeText
    0.64
    IContainer
    0.63
     springs
    0.63
    Activations Density 2.134%

    No Known Activations