© 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. 14737
    Prev
    Next
    INDEX
    Explanations

    numerical representations or identifiers (like numeric values and codes)

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

    Tokens starting with "f"

    np_acts-logits-general · gemini-2.0-flash

    two-letter sequences starting with f

    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
     تانيه
    -0.60
    MeasureSpec
    -0.50
     nakalista
    -0.49
    eleste
    -0.43
    ContentAsync
    -0.42
    nextDouble
    -0.41
     CreateTagHelper
    -0.40
     useAppContext
    -0.40
    ритори
    -0.39
    openzeppelin
    -0.39
    POSITIVE LOGITS
     fp
    1.08
     f
    1.05
     fs
    1.04
     FS
    1.04
     fc
    1.01
     FP
    1.01
     fb
    1.01
     fm
    1.00
     FC
    1.00
     FA
    1.00
    Activations Density 3.161%

    No Known Activations