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. 5-GEMMASCOPE-RES-16K
    6. 3425
    Prev
    Next
    INDEX
    Explanations

    structured data or code elements related to processing

    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
    følgelig
    -0.45
     nemlig
    -0.44
     تضيفلها
    -0.43
    مث
    -0.42
    えば
    -0.38
     været
    -0.38
     Balth
    -0.38
     
    -0.38
     nevo
    -0.37
    Otp
    -0.37
    POSITIVE LOGITS
     חיצוניים
    0.97
     ivelany
    0.97
    BagConstraints
    0.91
    EndProject
    0.90
    writerow
    0.87
    AndEndTag
    0.87
     doInBackground
    0.87
    detectChanges
    0.85
    AnimationsModule
    0.83
    InputBorder
    0.83
    Activations Density 0.186%

    No Known Activations