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. 16-GEMMASCOPE-RES-16K
    6. 9165
    Prev
    Next
    INDEX
    Explanations

    biological process terms related to cell staining and analysis

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

    Code or symbols

    np_acts-logits-general · gemini-2.0-flash

    foreign messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -1.03
    awtextra
    -0.94
    setVerticalGroup
    -0.79
    MigrationBuilder
    -0.77
     @"/
    -0.73
    RegressionTest
    -0.73
     SafeMath
    -0.71
    IsMutable
    -0.70
    WriteTagHelper
    -0.64
    WillAppear
    -0.64
    POSITIVE LOGITS
     المعيارى
    0.76
    ponses
    0.63
    DotNetBar
    0.55
    Портал
    0.52
    drawSprites
    0.50
    XtraEditors
    0.49
     springfox
    0.49
    الدراسه
    0.48
     вікі
    0.48
    Referanser
    0.48
    Activations Density 3.696%

    No Known Activations