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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 4710
    Prev
    Next
    INDEX
    Explanations

    instances of the word "need" or its variations, indicating a focus on necessity or requirement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colhead
    -0.84
     themſelves
    -0.73
     BoxDecoration
    -0.73
     itſelf
    -0.71
     Roskov
    -0.70
     linkovi
    -0.67
    󠁴
    -0.65
    Salsa
    -0.64
     Kome
    -0.64
    WriteTagHelper
    -0.63
    POSITIVE LOGITS
     needed
    1.75
     need
    1.72
    needed
    1.66
    NEED
    1.65
     Need
    1.65
     NEED
    1.62
    need
    1.55
     Needed
    1.54
    Need
    1.53
     needing
    1.50
    Activations Density 0.188%

    No Known Activations