© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3127
    Prev
    Next
    INDEX
    Explanations

    phrases related to chains or networks, particularly in the context of connection and disruption

    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
     Dummy
    -0.38
     клу
    -0.36
    本
    -0.35
     demi
    -0.34
    dummy
    -0.34
     представля
    -0.34
    交
    -0.34
     lust
    -0.33
     Meet
    -0.33
    Test
    -0.32
    POSITIVE LOGITS
     CHAIN
    0.99
     Chain
    0.97
     chain
    0.96
    Chain
    0.91
     chains
    0.91
     Chains
    0.86
    Chains
    0.82
    CHAIN
    0.81
    chains
    0.81
     Dark
    0.77
    Activations Density 0.150%

    No Known Activations