© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8461
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming features and bonuses

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

    Following less common words

    np_acts-logits-general · gemini-2.0-flash

    bonus features, finding treasures, know how

    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
    MessageTagHelper
    -0.42
    الإنجليزية
    -0.41
    âm
    -0.40
     invokingState
    -0.39
    WireFormatLite
    -0.39
     πολι
    -0.38
    бли
    -0.38
    Пото
    -0.38
     punta
    -0.38
    eba
    -0.38
    POSITIVE LOGITS
     itſelf
    0.93
     houſe
    0.90
     Majefty
    0.89
     Monfieur
    0.84
     pleaſure
    0.81
     AssemblyVersion
    0.81
     snippetHide
    0.80
     GenerationType
    0.78
     myſelf
    0.77
     multiplier
    0.77
    Activations Density 0.039%

    No Known Activations