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. 15-GEMMASCOPE-RES-16K
    6. 5037
    Prev
    Next
    INDEX
    Explanations

    concepts related to existence and reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hawatir
    -0.56
     يتيمه
    -0.55
    phemy
    -0.52
    Erstellt
    -0.52
     صوتيه
    -0.49
    τως
    -0.49
    stackrel
    -0.48
    enty
    -0.46
     triple
    -0.46
     fur
    -0.46
    POSITIVE LOGITS
     unavoidable
    1.07
     inescapable
    0.91
     inevitable
    0.77
     inevit
    0.76
    仕方ない
    0.72
     unavoid
    0.72
    仕方
    0.67
     realities
    0.67
    inev
    0.66
     utafitiHapana
    0.65
    Activations Density 0.242%

    No Known Activations