© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2320
    Prev
    Next
    INDEX
    Explanations

    instances of the word "continue" and related forms indicating ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mag
    -0.45
    webElementGuid
    -0.41
     bet
    -0.37
    chts
    -0.36
    aler
    -0.36
    PickerController
    -0.35
     tes
    -0.35
     motto
    -0.35
     ung
    -0.35
    下载附件
    -0.35
    POSITIVE LOGITS
     continuation
    2.95
    continue
    2.72
     continue
    2.69
     continuing
    2.63
     continuance
    2.59
     continued
    2.59
     Continuation
    2.55
     continu
    2.53
     continues
    2.48
    continued
    2.47
    Activations Density 0.180%

    No Known Activations