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. 8622
    Prev
    Next
    INDEX
    Explanations

    references to legal terms related to property

    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
    EndGlobalSection
    -0.47
    richTextPanel
    -0.45
    Filmografie
    -0.44
     Protección
    -0.43
    <sup>
    -0.43
    ...@
    -0.40
    *{
    -0.40
    <u>
    -0.39
    msgSender
    -0.39
    իա
    -0.39
    POSITIVE LOGITS
     فريبيس
    1.03
    ]")]
    0.89
    NOPQRST
    0.77
    endphp
    0.76
    醐
    0.73
    })();
    
    0.73
    enumi
    0.72
     fieldNum
    0.71
    ReusableCell
    0.70
     viewDidLoad
    0.69
    Activations Density 0.469%

    No Known Activations