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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57311
    Prev
    Next
    INDEX
    Explanations

    terms related to healing and its associated processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spindles
    -0.86
    Bertrand
    -0.79
    WithMany
    -0.78
    ttino
    -0.74
    wanzig
    -0.72
     Baillargeon
    -0.71
     مرئيه
    -0.71
     Bertrand
    -0.70
     Ayam
    -0.69
     Outs
    -0.68
    POSITIVE LOGITS
     healing
    1.39
     Healing
    1.33
     Heal
    1.29
     heal
    1.29
    Healing
    1.27
    Heal
    1.27
    healing
    1.26
     healed
    1.20
     heals
    1.18
    heal
    1.15
    Activations Density 0.006%

    No Known Activations