© 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. 14-GEMMASCOPE-RES-16K
    11. 2640
    Prev
    Next
    INDEX
    Explanations

    references to moral struggles between good and evil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Надо
    -0.92
     somebody
    -0.84
     cioè
    -0.84
     wierd
    -0.82
     stuff
    -0.82
     stupid
    -0.80
    Надо
    -0.79
     Somebody
    -0.79
    whatever
    -0.76
     idéia
    -0.75
    POSITIVE LOGITS
     impactful
    0.86
     prior
    0.85
     utilizing
    0.84
     utilizes
    0.79
     utilize
    0.78
     אשר
    0.77
     utilized
    0.74
     showcasing
    0.72
     welcher
    0.72
     transitioning
    0.70
    Activations Density 1.647%

    No Known Activations