© 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. 25-GEMMASCOPE-RES-16K
    11. 2922
    Prev
    Next
    INDEX
    Explanations

    instances of the word "help" and its variations in different contexts

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

    instances of the word "help" and its variants, indicating a focus on assistance and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    help
    -0.81
     help
    -0.79
    Help
    -0.79
     Help
    -0.72
     hjælp
    -0.71
     hjälp
    -0.60
    helping
    -0.60
     helping
    -0.59
     ayudas
    -0.58
     للمعارف
    -0.58
    POSITIVE LOGITS
    fully
    0.89
    desk
    0.81
     solve
    0.73
     alleviate
    0.71
    RenderAtEndOf
    0.70
     isInitialized
    0.67
     tremendously
    0.65
     define
    0.64
     facilitate
    0.63
     clarify
    0.62
    Activations Density 0.099%

    No Known Activations