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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16175
    Prev
    Next
    INDEX
    Explanations

    instructions and keywords related to cooking and food preparation

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

    procedural instructions and step-by-step processes.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     shewn
    -0.86
     पहु
    -0.81
     perchè
    -0.78
     focussed
    -0.76
     चीज़
    -0.72
    …..
    -0.71
     …..
    -0.71
     delà
    -0.70
     Whilst
    -0.69
     didalam
    -0.69
    POSITIVE LOGITS
     beziehungs
    0.72
     
    0.64
     
    0.64
    onsumsi
    0.55
     nong
    0.53
     nont
    0.50
     به‌عنوان
    0.49
    ␣
    0.48
     pertaining
    0.48
    . 
    0.47
    Activations Density 0.638%

    No Known Activations