© 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
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8055
    Prev
    Next
    INDEX
    Explanations

    references to networking and communication systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.63
     gevo
    -0.46
     Staates
    -0.42
    <!--[
    -0.41
     aggressiveness
    -0.40
    protoimpl
    -0.38
    centiles
    -0.38
     Agg
    -0.38
     الكبير
    -0.37
     parcial
    -0.36
    POSITIVE LOGITS
     Communications
    1.10
     Network
    1.09
     communications
    1.07
     Networks
    1.04
    Communications
    1.02
     network
    1.01
     COMMUNICATIONS
    1.00
     NETWORK
    1.00
     networks
    0.96
    communications
    0.94
    Activations Density 0.230%

    No Known Activations