© 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. 37-GEMMASCOPE-RES-16K
    6. 4947
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.70
     EconPapers
    -0.63
    Попис
    -0.61
     betweenstory
    -0.55
     fieldNum
    -0.55
     itſelf
    -0.55
    matchCondition
    -0.53
     Савезне
    -0.52
    hyrchwyd
    -0.52
     $_"
    -0.52
    POSITIVE LOGITS
    http
    1.00
    <eos>
    0.99
    https
    0.93
    ↵↵↵↵
    0.82
    ↵↵↵↵↵↵↵↵
    0.81
     http
    0.80
    ↵↵↵↵↵↵↵
    0.79
    Read
    0.78
    ↵↵↵↵↵↵
    0.77
    ↵↵↵↵↵
    0.76
    Activations Density 0.670%

    No Known Activations