© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5865
    Prev
    Next
    INDEX
    Explanations

    terms related to biological or chemical analysis and measurement techniques

    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
    MemoryWarning
    -0.92
    MigrationBuilder
    -0.82
     المعيارى
    -0.76
    AddTagHelper
    -0.76
    WriteTagHelper
    -0.74
    Tikang
    -0.73
     referenties
    -0.72
     ChromeDriver
    -0.70
    SourceChecksum
    -0.69
    protoimpl
    -0.66
    POSITIVE LOGITS
     including
    0.91
     such
    0.91
    ต่างๆ
    0.73
     waaronder
    0.68
    including
    0.68
    such
    0.68
     såsom
    0.67
    類
    0.65
    比如
    0.63
     telles
    0.62
    Activations Density 1.755%

    No Known Activations