© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 509
    Prev
    Next
    INDEX
    Explanations

    elements related to crime and thriller genres in films

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

    Movie/TV genre or category

    np_acts-logits-general · gemini-2.0-flash

    genres thriller action

    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
     Tapatalk
    -0.60
    ReusableCell
    -0.60
    новништво
    -0.59
    IonicModule
    -0.57
     whoſe
    -0.56
    出版年
    -0.55
     himſelf
    -0.53
    ünst
    -0.53
     обращения
    -0.52
    PageFactory
    -0.50
    POSITIVE LOGITS
     genre
    0.97
     thriller
    0.88
     genres
    0.80
    genre
    0.77
     Genre
    0.76
     drama
    0.72
     незавершена
    0.69
     adventure
    0.66
     comedy
    0.66
    riller
    0.66
    Activations Density 0.189%

    No Known Activations