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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29926
    Prev
    Next
    INDEX
    Explanations

    programming constructs and functions related to input and output operations

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

    identifiers are followed by values

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    原始内容存档于
    -0.69
     متعلقه
    -0.64
     оригіналу
    -0.57
    InOut
    -0.53
     glatt
    -0.51
    ponses
    -0.51
    <![
    -0.51
     Roskov
    -0.50
     veille
    -0.50
    pasto
    -0.50
    POSITIVE LOGITS
    UnusedPrivate
    0.66
    MessageOf
    0.63
    ContentAlignment
    0.49
    وأضاف
    0.48
    更に
    0.45
    addLine
    0.45
     adds
    0.45
     add
    0.44
     ++;
    0.44
    posables
    0.44
    Activations Density 0.022%

    No Known Activations