© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1428
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to long-term planning and outcomes

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

    "term" following "long" or related words/languages

    np_acts-logits-general · gemini-2.0-flash

    long-term duration outcomes

    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
     lenker
    -0.63
    󠁮
    -0.58
    tschafts
    -0.52
    MessageTagHelper
    -0.51
    Ngh
    -0.49
    /*
    -0.48
    CodeDom
    -0.48
     nahilalakip
    -0.48
    charCodeAt
    -0.47
    autique
    -0.47
    POSITIVE LOGITS
     longterm
    0.91
    term
    0.76
    長期
    0.69
     jangka
    0.68
    fristig
    0.67
    长期
    0.65
    Term
    0.59
    TERM
    0.58
    fristi
    0.58
     term
    0.57
    Activations Density 0.185%

    No Known Activations