Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 16379
    Prev
    Next
    INDEX
    Explanations

    instances of the word "conversation" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yordu
    -0.60
     pétrole
    -0.56
     plomb
    -0.54
     matériel
    -0.53
    iyle
    -0.52
    PROVIDER
    -0.52
    فحة
    -0.52
     églises
    -0.52
     McIntyre
    -0.52
    ostante
    -0.51
    POSITIVE LOGITS
     conversation
    2.42
     conversations
    2.15
     Conversation
    2.06
    conversation
    2.00
    Conversation
    1.97
     Conversations
    1.91
     CONVERS
    1.86
    Conversations
    1.77
     discussion
    1.77
     conversación
    1.74
    Activations Density 0.144%

    No Known Activations