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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27999
    Prev
    Next
    INDEX
    Explanations

    phrases expressing future possibilities and outcomes

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

    ending/final outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    numerusform
    -0.49
     مباشرة
    -0.48
     immédiatement
    -0.47
     immediate
    -0.47
     simple
    -0.46
     immediately
    -0.44
     instant
    -0.44
     dagegen
    -0.43
     immédi
    -0.43
    遽
    -0.43
    POSITIVE LOGITS
    eventually
    1.55
     eventually
    1.54
    Eventually
    1.50
     Eventually
    1.44
     uiteindelijk
    1.27
     ultimately
    1.25
     eventual
    1.23
     Ultimately
    1.13
    Ultimately
    1.06
     ultimate
    1.04
    Activations Density 0.243%

    No Known Activations