© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14898
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the process of transformation or progression in a narrative

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

    Beginning or starting point

    np_acts-logits-general · gemini-2.0-flash

    beginning from the start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.85
    yntaxException
    -0.82
    JspWriter
    -0.79
     redor
    -0.68
     frattempo
    -0.68
    脚注の使い方
    -0.68
    PyExc
    -0.67
    WriteTagHelper
    -0.66
    íncia
    -0.66
    UrlResolution
    -0.65
    POSITIVE LOGITS
     beginning
    0.84
     minute
    0.75
     moment
    0.75
     start
    0.73
     conception
    0.72
     inception
    0.65
     principio
    0.62
     concept
    0.61
     jump
    0.61
     day
    0.61
    Activations Density 0.126%

    No Known Activations