© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 97257
    Prev
    Next
    INDEX
    Explanations

    temporal transition words or phrases indicating sequential events

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

    later, subsequent, afterwards

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     snippetHide
    -0.72
    <pad>
    -0.63
    <unused79>
    -0.63
    <unused47>
    -0.63
    <unused23>
    -0.63
    <unused16>
    -0.63
    <unused28>
    -0.63
    <unused41>
    -0.63
    [@BOS@]
    -0.63
    <unused8>
    -0.63
    POSITIVE LOGITS
     later
    1.23
    later
    1.18
     afterward
    1.13
     später
    1.13
     afterwards
    1.09
     Posteriormente
    1.07
    Later
    1.07
     Later
    1.06
     później
    1.03
     posteriormente
    1.01
    Activations Density 0.042%

    No Known Activations