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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 5147
    Prev
    Next
    INDEX
    Explanations

    references to anniversaries and notable relationships

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

    Mathematical or technical expressions

    np_acts-logits-general · gemini-2.0-flash

    mutual interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    與
    -0.62
    与
    -0.61
     與
    -0.52
     vs
    -0.52
     与
    -0.51
    örg
    -0.50
    lerle
    -0.49
    versammlung
    -0.48
    との
    -0.47
     bekas
    -0.46
    POSITIVE LOGITS
     تضيفلها
    1.01
     mutual
    1.00
     nhau
    0.98
    mutual
    0.89
    protoimpl
    0.82
    Mutual
    0.82
     mutu
    0.82
    お互
    0.81
     exchanging
    0.80
     together
    0.79
    Activations Density 0.417%

    No Known Activations