© 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. 38-GEMMASCOPE-RES-16K
    6. 14782
    Prev
    Next
    INDEX
    Explanations

    terms related to mana and healing mechanics in gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikipédia
    -0.33
    bigliamento
    -0.33
     botanique
    -0.32
     Official
    -0.31
    libft
    -0.30
     official
    -0.30
     OFFICIAL
    -0.30
    RTEE
    -0.29
    rslt
    -0.29
     ilmo
    -0.29
    POSITIVE LOGITS
     offensively
    0.73
     synerg
    0.71
     synergy
    0.69
     matchups
    0.68
     synergies
    0.67
     matchup
    0.66
     synergistic
    0.66
     defensively
    0.65
     punish
    0.65
     oppressive
    0.62
    Activations Density 0.084%

    No Known Activations