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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 93654
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to phases and transitions in materials or chemical processes

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

    phase stabilization and settings

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    <bos>
    -0.46
    Rüyada
    -0.44
     britannique
    -0.42
    받
    -0.41
     scottish
    -0.41
     cuantas
    -0.40
     Escri
    -0.40
     cuánt
    -0.40
     australian
    -0.39
     الدولى
    -0.39
    POSITIVE LOGITS
     Phase
    1.32
    Phase
    1.32
     phase
    1.27
    phase
    1.20
     PHASE
    1.16
     phases
    1.11
     Phases
    1.08
    PHASE
    1.05
    phases
    1.00
    Phases
    0.99
    Activations Density 0.024%

    No Known Activations