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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 43877
    Prev
    Next
    INDEX
    Explanations

    phrases that denote significant achievements or notable advancements in various fields

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

    reaching important milestones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     always
    -0.33
     selalu
    -0.28
     همیشه
    -0.27
     שם
    -0.27
    rière
    -0.27
     films
    -0.26
     invece
    -0.25
     warum
    -0.25
     podczas
    -0.25
    总是
    -0.24
    POSITIVE LOGITS
     milestone
    0.72
    
    0.69
     kaarangay
    0.67
    milestone
    0.65
    RTSN
    0.65
    ChrTalk
    0.64
     '\\;'
    0.63
    󠁴
    0.63
     breakthrough
    0.62
     precedent
    0.62
    Activations Density 0.037%

    No Known Activations