© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13127
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific descriptions and characteristics of materials or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.94
     Chwiliwch
    -0.93
    帖最后由
    -0.92
    OGND
    -0.91
     Administrativna
    -0.90
    ReusableCell
    -0.87
     utafitiHapana
    -0.87
     للاسماء
    -0.86
     ProtoMessage
    -0.86
    :✨
    -0.85
    POSITIVE LOGITS
    ’
    0.50
     ſta
    0.44
     ſte
    0.43
     rodríguez
    0.40
     robusta
    0.38
     ‘
    0.38
     castel
    0.37
     ſtre
    0.36
     tranſ
    0.36
     ſtand
    0.35
    Activations Density 3.039%

    No Known Activations