Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1233
    Prev
    Next
    INDEX
    Explanations

    adverbs, particularly those conveying intensity or manner of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.58
    yship
    -0.58
    OGND
    -0.56
    WhereInput
    -0.56
     translateY
    -0.55
    BeginContext
    -0.54
    verwijspagina
    -0.54
     ones
    -0.53
    èdia
    -0.53
     برانيه
    -0.53
    POSITIVE LOGITS
    successfully
    0.76
     excitedly
    0.71
     calmly
    0.70
    ebly
    0.67
     proudly
    0.67
     confidently
    0.65
    slowly
    0.65
    correctly
    0.64
     cheerfully
    0.64
     efficiently
    0.64
    Activations Density 0.363%

    No Known Activations