© 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. 30-GEMMASCOPE-RES-16K
    6. 12335
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to email and messaging integrations

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

    Amazon Kinesis Data Streams and similar services

    np_acts-logits-general · gemini-2.0-flash

    JMS, Kinesis, message topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.34
     virgen
    -0.32
    lysninger
    -0.32
    unzel
    -0.31
     coastal
    -0.27
    kozó
    -0.27
     pad
    -0.27
    raszamy
    -0.26
     renon
    -0.26
     matriz
    -0.26
    POSITIVE LOGITS
     topic
    0.91
     Topic
    0.86
    Topic
    0.84
     TOPIC
    0.83
     topics
    0.82
    topic
    0.80
     queues
    0.77
     queue
    0.77
    TOPIC
    0.77
     Topics
    0.76
    Activations Density 0.334%

    No Known Activations