© 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. 16-GEMMASCOPE-RES-16K
    11. 1098
    Prev
    Next
    INDEX
    Explanations

    elements related to sacrifice and transformation in narratives

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

    Followed by "Wall" or punctuation

    np_acts-logits-general · gemini-2.0-flash

    fourth wall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ρίες
    -0.50
    WithFormat
    -0.46
    }}"
    -0.45
    gration
    -0.43
     perciò
    -0.43
    "=>"
    -0.41
     possesso
    -0.40
    andung
    -0.39
    سری
    -0.39
    ContentAsync
    -0.39
    POSITIVE LOGITS
    Personensuche
    0.83
    newswire
    0.65
    发表于
    0.63
     &___
    0.63
    enschappelijke
    0.63
    ItemBackground
    0.63
    sunter
    0.62
     wikipagina
    0.61
    canestro
    0.61
     allAfrica
    0.60
    Activations Density 0.092%

    No Known Activations