© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4673
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to scientific research methodologies and analyses

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

    Mass spectrometry and related techniques

    np_acts-logits-general · gemini-2.0-flash

    mass spectrometry imaging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CSL
    -0.45
     ECON
    -0.35
    antaine
    -0.35
     reaſon
    -0.35
     Mosaic
    -0.34
    tagHelperRunner
    -0.34
    StoryboardSegue
    -0.33
     thyself
    -0.33
    ########.
    -0.33
    RTLD
    -0.32
    POSITIVE LOGITS
     mass
    0.63
    mass
    0.62
     ionization
    0.58
    masses
    0.54
     analytical
    0.54
     hmot
    0.54
     Mass
    0.52
     masses
    0.52
    deutig
    0.50
    ionization
    0.50
    Activations Density 0.525%

    No Known Activations