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. 7-GEMMASCOPE-RES-16K
    6. 15280
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions

    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
    <eos>
    -0.49
     tema
    -0.40
     
    -0.38
     Leben
    -0.36
    ')){
    -0.36
     la
    -0.36
     op
    -0.36
    IsContent
    -0.36
    рам
    -0.36
     spend
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.92
     müßte
    0.90
     daß
    0.86
     muß
    0.85
    رشف
    0.83
    发表于
    0.82
     EdgeInsets
    0.82
     Monfieur
    0.82
     pleaſure
    0.81
     Majefty
    0.81
    Activations Density 1.856%

    No Known Activations