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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 2357
    Prev
    Next
    INDEX
    Explanations

    formatting commands related to centering and splitting in LaTeX documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.55
    }?>
    -0.51
    }</
    -0.50
    sockfd
    -0.49
    LookAnd
    -0.47
     plan
    -0.47
     =&
    -0.46
    }"
    -0.46
     idea
    -0.45
    makeatother
    -0.45
    POSITIVE LOGITS
    center
    1.66
    CENTER
    1.27
    centers
    1.21
    Center
    1.17
     center
    1.07
     CENTER
    1.05
     centers
    1.01
    Centers
    0.96
    ParallelGroup
    0.96
     Centers
    0.96
    Activations Density 0.058%

    No Known Activations