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. 15-GEMMASCOPE-RES-16K
    6. 8600
    Prev
    Next
    INDEX
    Explanations

    references to software-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hưng
    -0.67
     Jerusalén
    -0.67
     Tare
    -0.63
    Isolate
    -0.63
     Shanks
    -0.61
     Rebirth
    -0.61
    unci
    -0.61
     Recons
    -0.60
     annunci
    -0.60
    adpleegd
    -0.59
    POSITIVE LOGITS
     software
    1.19
     Software
    1.15
     softwares
    1.05
    SOFTWARE
    1.04
    Software
    1.02
    oftware
    1.02
    software
    1.00
     SOFTWARE
    0.95
     软件
    0.95
     pinulongan
    0.91
    Activations Density 0.066%

    No Known Activations