© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 12325
    Prev
    Next
    INDEX
    Explanations

    language associated with violence and horror

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.70
    IntoConstraints
    -0.69
    ┐
    -0.68
     createContext
    -0.67
    InputTagHelper
    -0.66
     auprès
    -0.64
     GetEnumerator
    -0.63
     AspNetCore
    -0.63
    InjectMocks
    -0.62
     škola
    -0.61
    POSITIVE LOGITS
     horrible
    1.38
     horrific
    1.37
     terrible
    1.35
     horror
    1.34
     horrifying
    1.26
     terror
    1.23
    horror
    1.20
     horrors
    1.20
     Terrible
    1.19
     awful
    1.19
    Activations Density 0.221%

    No Known Activations