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. 22-GEMMASCOPE-RES-16K
    6. 14091
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to materials analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.56
     mapStateToProps
    -0.55
    aktionen
    -0.55
    GetEnumerator
    -0.52
    mtrl
    -0.51
     Reyn
    -0.50
    issez
    -0.50
     sabato
    -0.49
    Tikang
    -0.49
    ніципа
    -0.49
    POSITIVE LOGITS
     peaks
    1.40
     peak
    1.38
    peak
    1.22
     Peaks
    1.19
    peaks
    1.17
    Peak
    1.16
     Peak
    1.13
     peaking
    0.99
     peaked
    0.97
    ピーク
    0.94
    Activations Density 1.257%

    No Known Activations