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. 7-GEMMASCOPE-RES-16K
    6. 11744
    Prev
    Next
    INDEX
    Explanations

    code that manipulates or checks the status of data structures, particularly focusing on conditions related to data size and insertion methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    łby
    -0.60
    gouv
    -0.55
    ellemző
    -0.55
     Feldman
    -0.54
     centrales
    -0.54
    dehydes
    -0.52
    BeginInit
    -0.50
     चीज़
    -0.50
    WireFormatLite
    -0.49
    vlog
    -0.48
    POSITIVE LOGITS
    +#+#
    1.10
    rrggbb
    0.87
     незавершена
    0.74
     linkovi
    0.60
    Clik
    0.58
     betweenstory
    0.57
     jPanel
    0.56
     صوتيه
    0.55
    didSet
    0.55
     <",
    0.54
    Activations Density 0.271%

    No Known Activations