© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10949
    Prev
    Next
    INDEX
    Explanations

    references to ghosts and ghostly themes or characters

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

    "ghost" (or similar concepts)

    np_acts-logits-general · gemini-2.0-flash

    ghostly or haunted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.54
    StructEnd
    -0.50
     '\\;'
    -0.47
    wapV
    -0.46
    WireFormatLite
    -0.45
    hilt
    -0.45
     SDM
    -0.45
    Autoritní
    -0.44
    ltr
    -0.44
    reth
    -0.44
    POSITIVE LOGITS
     ghost
    1.75
     ghosts
    1.59
    ghost
    1.58
     Ghost
    1.57
    Ghost
    1.57
     fantasmas
    1.35
     fantasma
    1.30
    Ghosts
    1.28
     ghostly
    1.25
     Ghosts
    1.23
    Activations Density 0.386%

    No Known Activations