© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7114
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular structures and processes in biological contexts

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

    "lead", plus a following action

    np_acts-logits-general · gemini-2.0-flash

    lead displacement, pattern deformation, sample selection, channel opening, model evaluation, complex assembly, particle size, signal overlap, cell mobility, beam squint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     définiti
    -0.75
     aussitôt
    -0.67
     enfans
    -0.64
     autorité
    -0.62
     donnés
    -0.61
     épreuve
    -0.60
     termica
    -0.59
     autorisés
    -0.58
    IBOutlet
    -0.58
     élevés
    -0.57
    POSITIVE LOGITS
     size
    0.62
     sizes
    0.62
    SceneManagement
    0.61
    bindingNavigator
    0.60
     selection
    0.58
    astéroïdes
    0.58
     management
    0.58
     utafitiHapana
    0.58
    -
    0.57
    unknownFields
    0.56
    Activations Density 0.888%

    No Known Activations