© 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. 6610
    Prev
    Next
    INDEX
    Explanations

    character names and their associated roles in a narrative context

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

    Kyuranger/Sentai-related text

    np_acts-logits-general · gemini-2.0-flash

    Super Sentai team names

    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
     المعيارى
    -0.61
    etCode
    -0.55
    
    -0.54
    sendKeys
    -0.53
    UserScript
    -0.53
    ]^{-
    -0.51
     anticoag
    -0.51
    MLLoader
    -0.49
    findpost
    -0.49
    AppRoutingModule
    -0.49
    POSITIVE LOGITS
     goku
    0.76
     Saiyan
    0.74
    Goku
    0.67
     Goku
    0.63
     rallado
    0.62
     Gok
    0.59
     Fighter
    0.59
     Kombat
    0.57
    スーパー
    0.56
     aéreo
    0.56
    Activations Density 0.280%

    No Known Activations