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. 6499
    Prev
    Next
    INDEX
    Explanations

    phrases related to necessity and obligation

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

    Comes after "need to" or "needs to"

    np_acts-logits-general · gemini-2.0-flash

    need to verb

    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
     onCancelled
    -0.42
     "\""
    -0.38
     nabízí
    -0.37
    culable
    -0.36
     Völ
    -0.35
     proyec
    -0.35
     colorWith
    -0.34
     erbjuder
    -0.34
    最快更新
    -0.34
     jagung
    -0.33
    POSITIVE LOGITS
     Нужно
    0.81
    Need
    0.78
    needs
    0.77
     need
    0.77
     needs
    0.76
     Need
    0.75
     нужно
    0.74
     needed
    0.73
    needed
    0.73
    Needed
    0.73
    Activations Density 0.106%

    No Known Activations