Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 7186
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to computational algorithms and statistical methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.56
     Jans
    -0.44
     oprot
    -0.43
     venuto
    -0.42
    fizierung
    -0.41
     yıl
    -0.40
    <eos>
    -0.40
     calcetines
    -0.40
    haup
    -0.40
    đen
    -0.39
    POSITIVE LOGITS
     problem
    1.06
     problema
    0.93
    problem
    0.93
     Probl
    0.90
     ujednoznacz
    0.90
     задача
    0.89
    problema
    0.88
     problème
    0.88
     probleem
    0.85
     Problem
    0.85
    Activations Density 0.972%

    No Known Activations