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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6427
    Prev
    Next
    INDEX
    Explanations

    temporal phrases indicating sequences of events

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

    "later"

    np_acts-logits-general · gemini-2.0-flash

    later followed by subsequent event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.61
     snippetHide
    -0.54
    setupUi
    -0.49
     vectorstock
    -0.48
    %)$
    -0.48
     myſelf
    -0.48
     pleaſure
    -0.47
     faſt
    -0.47
    EXC
    -0.46
     COVID
    -0.45
    POSITIVE LOGITS
     later
    1.98
    later
    1.91
    Later
    1.84
     Later
    1.80
     später
    1.71
     LATER
    1.59
     späteren
    1.47
     senere
    1.39
     pozdě
    1.35
     позже
    1.33
    Activations Density 0.184%

    No Known Activations