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. 4-GEMMASCOPE-RES-16K
    6. 10994
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to measurements or rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sidemargin
    -0.59
     wireType
    -0.58
     consultato
    -0.58
    sizeCache
    -0.52
    =$?
    -0.52
    Démographie
    -0.52
     units
    -0.51
    Datuak
    -0.50
    abetes
    -0.50
    numerusform
    -0.50
    POSITIVE LOGITS
    EndInit
    0.64
    olished
    0.56
     متعلقه
    0.56
     صوتيه
    0.52
    yonel
    0.51
    OrEmpty
    0.50
    otry
    0.49
    enciaga
    0.48
     Sodom
    0.48
    IUrlHelper
    0.48
    Activations Density 1.734%

    No Known Activations