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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14273
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to nuclear magnetic resonance (NMR) spectroscopy

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

    Scientific instruments and methods

    np_acts-logits-general · gemini-2.0-flash

    scientific analysis and imaging techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="@+
    -0.51
     dichiarato
    -0.39
    ngrx
    -0.38
     cappello
    -0.36
     malheur
    -0.36
    SwitchCompat
    -0.36
     объя
    -0.36
    허
    -0.35
    पया
    -0.35
     postIndex
    -0.34
    POSITIVE LOGITS
     probing
    0.57
     techniques
    0.57
     microscopy
    0.54
     instrumentation
    0.53
     scanner
    0.52
     laboratory
    0.51
     diagnostics
    0.50
     spectrometry
    0.50
     spectroscopy
    0.49
     spectrometer
    0.49
    Activations Density 1.325%

    No Known Activations